WO2024144592A1 - Weld penetration prediction system and method in robotic gas metal arc welding cells - Google Patents
Weld penetration prediction system and method in robotic gas metal arc welding cells Download PDFInfo
- Publication number
- WO2024144592A1 WO2024144592A1 PCT/TR2023/051318 TR2023051318W WO2024144592A1 WO 2024144592 A1 WO2024144592 A1 WO 2024144592A1 TR 2023051318 W TR2023051318 W TR 2023051318W WO 2024144592 A1 WO2024144592 A1 WO 2024144592A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- welding
- weld
- penetration
- unit
- prediction system
- Prior art date
Links
- 238000003466 welding Methods 0.000 title claims abstract description 67
- 230000035515 penetration Effects 0.000 title claims abstract description 37
- 239000002184 metal Substances 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 title claims description 11
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 11
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 238000012800 visualization Methods 0.000 claims abstract description 4
- 238000003672 processing method Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009658 destructive testing Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- B23K9/095—Monitoring or automatic control of welding parameters
- B23K9/0953—Monitoring or automatic control of welding parameters using computing 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
- 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
- B23K31/006—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 using of neural networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- Another object of the invention is to provide the operator and quality officer with the predicted penetration value at each point online by using analysis algorithms with the data collected from the robot and welding unit during the lap-joint gas metal arc welding operation with the online data collection system.
- the invention is a welding penetration prediction system in robotic gas metal arc welding cells, characterized by comprising:
- the invention relates to a system and method for predicting weld penetration and developing predictive quality operations in lap-joint welding operations in robotic gas metal arc welding cells.
- Robot control unit (1 ) used in the inventive system is the unit that manages the welding operation and controls robot (5) and welding unit (2).
- the welding unit (2) is the unit that performs the welding operation.
- Welding part (3) is the part to be gas metal arc welded.
- Penetration prediction system (4) is a data acquisition, processing and visualization unit. It is a system that controls the weld penetration and decides whether the weld is healthy or not by using all the data (current, voltage, resistance, welding speed, wire speed, gas flow rate, robot speed, robot position) collected from the welding unit (2) and robot control unit (1) with a previously taught machine learning or signal processing based system, using welding or sensor data received online, controlling the weld penetration and deciding whether the weld is healthy or not, enabling the user to control the process and cost advantage without interrupting the quality of the weld part.
- Communication system (6) is a system that transmits the data collected through the robot control unit (1 ) and the welding unit (2) to the penetration prediction system (4).
- the communication system (6) can transmit the data either wired or wirelessly.
- the welding operation starts via the robot control unit (1) when operator triggers.
- the robot control unit (1) communicates with the welding unit (2) and makes it active.
- the data is collected in the penetration prediction system (4) via the communication system (6).
- the penetration prediction system (4) predicts current penetration with algorithms created with the data collected in the past and predicts for the user the welding quality through interface without using any visual data or sensors with the current, voltage, gas flow rate, welding speed, wire feed speed and robot position data collected from the machine. By notifying the welding operator of the predictions it has made, it can stop the welding operation depending on the command or only inform the operator.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Manipulator (AREA)
Abstract
Welding penetration prediction system in robotic gas metal arc welding cells, characterized by comprising a robot control unit (1) which manages welding operation and controls robot (5) and welding unit (2), the welding unit (2) which carries out the welding operation to welding part (3), penetration prediction system (4) that provides data collection, processing and visualization, which checks the weld penetration and decides whether the weld is healthy or not, using all the data collected from the welding unit (2) and the robot control unit (1) and the weld or sensor data received online with a machine learning or signal processing based system, communication system (6) that transmits the data collected via the robot control unit (1) and the welding unit (2) to the penetration prediction system (4).
Description
WELD PENETRATION PREDICTION SYSTEM AND METHOD IN ROBOTIC GAS METAL
ARC WELDING CELLS
Technical Field
The invention relates to a system and method for predicting weld penetration and developing predictive quality operations in lap-joint welding operations in robotic gas metal arc welding cells.
State of the Art
Today, there is no non-destructive testing in gas metal arc welding operations. After these operations, quality measurement is carried out by destructive testing of some parts. In addition, there is no system/algorithm that performs online non-destructive testing in gas metal arc welding. There is also no system/algorithm that performs online penetration measurement and quality testing in gas metal arc welding. Therefore, the control and prediction of weld quality or weld penetration in current gas metal arc welding operations are insufficient.
In the application JP2005349422A, which is found as a result of technical research, only the outer surface of the weld is controlled, and no other parameters are used. In the application JP2005349422A, continuous painting is performed, and image processing is performed to control and analyze the shape of the visible surfaces of the weld. The main parameter in the mentioned application is the photograph. The system works by using photographs or visual data. The purpose is to perform visual conformity checks.
As can be seen, the system is related to the control of the outer surface of the weld and does not mention a structure that can provide a solution to the disadvantages mentioned above.
As a result, due to the above-mentioned negativities and the inadequacy of the existing solutions on the subject, it has become necessary to make a development in the relevant technical field.
Object of Invention
The invention aims to provide a structure having different technical features which brings a new opening in this field, different from the structures used in the present art.
The primary object of the invention is to provide a system and method for the prediction of weld penetration and the development of predictive quality operations in lap-joint welding operations in robotic gas metal arc welding cells.
An object of the invention is to perform measurement predictions and quality analysis in the invisible region (penetration) of the weld within the part, using data acquisition and artificial intelligence methods.
Another object of the invention is to provide a system that operates using current, voltage, wire feed speed, welding speed parameters and machine learning methods.
Another object of the invention is to provide the operator and quality officer with the predicted penetration value at each point online by using analysis algorithms with the data collected from the robot and welding unit during the lap-joint gas metal arc welding operation with the online data collection system.
A further object of the invention is to improve the cost and additional process steps by eliminating the need for part cutting.
In order to fulfil the above-described objects, the invention is a welding penetration prediction system in robotic gas metal arc welding cells, characterized by comprising:
• a robot control unit which manages welding operation and controls robot and welding unit,
• the welding unit which carries out the welding operation to welding part,
• penetration prediction system that provides data collection, processing and visualization, which checks the weld penetration and decides whether the weld is healthy or not, using all the data collected from the welding unit and the robot control unit and the weld or sensor data received online with a machine learning or signal processing based system,
• communication system that transmits the data collected via the robot control unit and the welding unit to the penetration prediction system.
The structural and characteristic features and all advantages of the invention will be more clearly understood by means of the figures given below and the detailed description written by making references to these figures, and therefore, the evaluation should be made by taking these figures and detailed description into consideration.
Figures to Help Understanding the Invention
Figure 1 is a general view of the inventive system.
The figures are not necessarily to scale, and details not necessary for understanding the present invention may be omitted. Furthermore, elements which are at least substantially identical or have at least substantially identical functions are indicated by the same number.
Description of Part References
1. Robot Control Unit
2. Welding Unit
3. Welding Part
4. Penetration Prediction System
5. Robot
6. Communication System
Detailed Description of the Invention
In this detailed description, the preferred embodiments of the invention are described only for the purpose of a better understanding of the subject matter and without any limiting effect.
The invention relates to a system and method for predicting weld penetration and developing predictive quality operations in lap-joint welding operations in robotic gas metal arc welding cells.
Robot control unit (1 ) used in the inventive system is the unit that manages the welding operation and controls robot (5) and welding unit (2).
The welding unit (2) is the unit that performs the welding operation.
Welding part (3) is the part to be gas metal arc welded.
Penetration prediction system (4) is a data acquisition, processing and visualization unit. It is a system that controls the weld penetration and decides whether the weld is healthy or not by using all the data (current, voltage, resistance, welding speed, wire speed, gas flow rate, robot speed, robot position) collected from the welding unit (2) and robot control unit (1) with a previously taught machine learning or signal processing based system, using welding or sensor data received online, controlling the weld penetration and deciding whether the weld is healthy or not, enabling the user to control the process and cost advantage without interrupting the quality of the weld part.
Communication system (6) is a system that transmits the data collected through the robot control unit (1 ) and the welding unit (2) to the penetration prediction system (4). The communication system (6) can transmit the data either wired or wirelessly.
The working principle of the inventive system is as follows;
The welding operation starts via the robot control unit (1) when operator triggers. The robot control unit (1) communicates with the welding unit (2) and makes it active. While the robot (5) is welding on the welding part (3), the data is collected in the penetration prediction system (4) via the communication system (6). The penetration prediction system (4) predicts current penetration with algorithms created with the data collected in the past and predicts for the user the welding quality through interface without using any visual data or sensors with the current, voltage, gas flow rate, welding speed, wire feed speed and robot position data collected from the machine. By notifying the welding operator of the predictions it has made, it can stop the welding operation depending on the command or only inform the operator.
The process steps performed with the inventive system are as follows:
• transferring the data collected by robot control unit (1) and welding unit (2) online via communication system (6) to penetration prediction system (4),
• predicting quality and penetration of the weld by processing the data received via the communication system (6) according to previously taught machine learning and signal processing methods,
• the system decides to stop the welding operation or informs the user about the weld quality according to the data generated on the penetration prediction system (4).
Claims
1. Welding penetration prediction system in robotic gas metal arc welding cells, characterized by comprising:
• a robot control unit (1 ) which manages welding operation and controls robot (5) and welding unit (2),
• the welding unit (2) which carries out the welding operation to welding part (3),
• penetration prediction system (4) that provides data collection, processing and visualization, which checks the weld penetration and decides whether the weld is healthy or not, using all the data collected from the welding unit (2) and the robot control unit (1 ) and the weld or sensor data received online with a machine learning or signal processing based system,
• communication system (6) that transmits the data collected via the robot control unit (1) and the welding unit (2) to the penetration prediction system (4).
2. The system according to claim 1 , characterized by comprising the penetration prediction system (4) for receiving and processing current, voltage, resistance, welding speed, wire speed, gas flow rate, robot speed, robot position data from the welding unit (2) and the robot control unit (1).
3. Weld penetration prediction method in robotic gas metal arc welding cells, characterized by comprising following process steps:
• transferring the data collected by robot control unit (1) and welding unit (2) online via communication system (6) to penetration prediction system (4),
• predicting quality and penetration of the weld by processing the data received via the communication system (6) according to previously taught machine learning and signal processing methods,
• the system decides to stop the welding operation or informs the user about the weld quality according to the data generated on the penetration prediction system (4).
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TR2022/021086 | 2022-12-28 | ||
| TR2022021086 | 2022-12-28 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024144592A1 true WO2024144592A1 (en) | 2024-07-04 |
Family
ID=91718964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/TR2023/051318 WO2024144592A1 (en) | 2022-12-28 | 2023-11-13 | Weld penetration prediction system and method in robotic gas metal arc welding cells |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2024144592A1 (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10500668B2 (en) * | 2015-07-31 | 2019-12-10 | Fanuc Corporation | Machine learning device, arc welding control device, arc welding robot system, and welding system |
| US20210078093A1 (en) * | 2019-09-12 | 2021-03-18 | Illinois Tool Works Inc. | System and methods for labeling weld monitoring time periods using machine learning techniques |
| WO2022019013A1 (en) * | 2020-07-20 | 2022-01-27 | 株式会社神戸製鋼所 | Machine learning device, laminate molding system, machine learning method for welding condition, welding condition determination method, and program |
-
2023
- 2023-11-13 WO PCT/TR2023/051318 patent/WO2024144592A1/en unknown
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10500668B2 (en) * | 2015-07-31 | 2019-12-10 | Fanuc Corporation | Machine learning device, arc welding control device, arc welding robot system, and welding system |
| US20210078093A1 (en) * | 2019-09-12 | 2021-03-18 | Illinois Tool Works Inc. | System and methods for labeling weld monitoring time periods using machine learning techniques |
| WO2022019013A1 (en) * | 2020-07-20 | 2022-01-27 | 株式会社神戸製鋼所 | Machine learning device, laminate molding system, machine learning method for welding condition, welding condition determination method, and program |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105855743B (en) | A kind of Weld pool dynamic process on-line monitoring system and method | |
| EP3812105A1 (en) | Artificial intelligence architecture for industrial welding | |
| CN112855266B (en) | Intelligent monitoring and autonomous collaborative machine following device of coal mining machine and inspection platform system | |
| Liu et al. | Control of human arm movement in machine-human cooperative welding process | |
| Zhang et al. | Adaptive intelligent welding manufacturing | |
| CN102728932B (en) | Method and device for automatically optimizing electric-arc welding process parameters | |
| Kim et al. | Mathematical models for control of weld bead penetration in the GMAW process | |
| US20200363787A1 (en) | Method for automatically determining optimum welding parameters for carrying out a weld on a workpiece | |
| Yu et al. | How to accurately monitor the weld penetration from dynamic weld pool serial images using CNN-LSTM deep learning model? | |
| CN114012210A (en) | Deposition quality judgment system and method in electric arc additive process | |
| CA1202690A (en) | Method and apparatus for detecting the onset of melting in a resistance spot weld | |
| JP2023095820A (en) | Generation method of learning model, control device, learning model, welding system and program | |
| Barot et al. | Process monitoring and internet of things feasibility for submerged arc welding: State of art | |
| WO2024144592A1 (en) | Weld penetration prediction system and method in robotic gas metal arc welding cells | |
| KR101677162B1 (en) | A welding apparatus | |
| US20240246151A1 (en) | Methods for Additive Manufacturing of a Component | |
| Kolahan et al. | Modeling and optimization of MAG welding for gas pipelines using regression analysis and simulated annealing algorithm | |
| CN114951706B (en) | Intelligent powder spreading method and system for laser selective melting | |
| Ma et al. | Mixed logical dynamical model for back bead width prediction of pulsed GTAW process with misalignment | |
| KR102236411B1 (en) | Steel welding apparatus | |
| Zhang et al. | An easy method of image feature extraction for real-time welding defects detection | |
| US20190084070A1 (en) | Mig welding system | |
| CN114083091A (en) | Narrow and deep space internal welding early warning monitoring method based on cloud edge and end cooperation | |
| Chen | Visual information acquirement and real-time control methodologies for weld pool dynamics during pulsed GTAW | |
| Barot et al. | Development and investigations of IoT enabled wire feed and weld speed measurement for submerged arc welding |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23913194 Country of ref document: EP Kind code of ref document: A1 |