CN116451045B - Welding process steady-state current calculation method - Google Patents
Welding process steady-state current calculation method Download PDFInfo
- Publication number
- CN116451045B CN116451045B CN202310701879.1A CN202310701879A CN116451045B CN 116451045 B CN116451045 B CN 116451045B CN 202310701879 A CN202310701879 A CN 202310701879A CN 116451045 B CN116451045 B CN 116451045B
- Authority
- CN
- China
- Prior art keywords
- current
- welding
- average value
- clustering
- point
- 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.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 133
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004364 calculation method Methods 0.000 title claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 7
- 238000012216 screening Methods 0.000 claims abstract description 5
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000008033 biological extinction Effects 0.000 abstract description 3
- 238000007796 conventional method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000012467 final product Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000012795 verification 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/0092—Arrangements for measuring currents or voltages or for indicating presence or sign thereof measuring current only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Plasma & Fusion (AREA)
- Probability & Statistics with Applications (AREA)
- Arc Welding Control (AREA)
Abstract
The invention discloses a steady-state current calculation method in a welding process, which comprises the steps of firstly collecting current data in the operation process of a welding machine in real time based on a current sensor, and capturing a starting current point and an ending current point of each welding action; filtering the conditions of independent spot welding and continuous spot welding, screening long welding seams, and calculating the current stable value of the long welding seams; clustering is carried out based on the obtained current stable values of the long weld joints, and the current average value in the period of time is calculated based on the clustering result; finally, comparing the current average value of each type of clustering result with the current range in the welding process specification WPS, and judging the current quality; the method provided by the invention filters the spot welding condition in general welding and the unstable current condition during arcing and arc extinction, and compared with the traditional steady-state current calculation, the method provided by the invention is more accurate, can better reflect the current state during actual welding, and provides more accurate comparison basis for WPS comparison.
Description
Technical Field
The invention belongs to the technical field of intelligent welding, and particularly relates to a steady-state current calculation method in a welding process.
Background
In the industrial welding process, along with the large-scale application of robot welding, the traditional welding operation is developing towards the scale and standardization. The production of mass welded products is not separated from the standard welding operation flow. Corresponding welding process regulations (WPS) need to be formulated for different processes. In the actual welding process, the execution condition of the WPS directly relates to the specification of the welding operation and the quality of the final product, and is the basis which the welding operation must follow.
In the welding process of the robot, due to frequent arc starting and extinguishing and a large number of spot welding scenes, if the current value of each process is simply captured and averaged based on a current sensor, the current value is affected by the too low current value, so that the calculated overall current effective value is lower, and the current is inaccurate for judging whether the current meets the WPS (WPS) or not when the welding seam is actually welded. Therefore, a method is needed to remove the influence on the effective current value under the conditions of arcing, arc extinction and spot welding, and further calculate the effective current value when each process is truly stable, and the effective current value is used as a basis for evaluating the current quality.
Disclosure of Invention
The invention aims to: aiming at the problems in the background art, the invention provides a steady-state current calculation method in a welding process, which eliminates the current abrupt change condition during continuous spot welding, arcing and arc extinction on the basis of capturing a plurality of welding actions, only calculates the average value of a current stable section as a judgment basis, and further provides a more accurate current effective value as a standard for evaluating the welding current quality.
The technical scheme is as follows: a welding process steady state current calculation method comprising the steps of:
step S1, collecting current data in the running process of a welding machine in real time based on a current sensor, and capturing a starting current point and an ending current point of each welding action;
s2, filtering the conditions of independent spot welding and continuous spot welding, screening a long welding line, and calculating the current stable value of the long welding line;
step S3, clustering the current stable values of the long weld joints obtained in the step S2, and calculating a current average value in a preset time period based on a clustering result;
and S4, comparing the current average value of each type of clustering result with the current range in the welding technological specification WPS, and judging the current quality.
Further, the method for capturing the starting current point and the ending current point of the welding process in the step S1 includes:
s1.1, extracting all current point sequences with current greater than a threshold value th1, and eliminating non-arcing points and other interference points in the current sequences;
step S1.2, taking a first current point in the current point sequence as a starting point of a welding action, traversing the rest current point sequence, and considering that the current welding action is finished when a blank current point exists between the current point and the rear current point; taking the former current point as the ending point of the previous welding action, and taking the latter current point as the starting point of the next welding action;
and S1.3, repeating the steps to obtain a plurality of current intervals representing a plurality of welding actions.
Further, the method for screening the long weld joint in the step S2 includes:
step S2.1, traversing each welding action interval, and setting a preset threshold th2 of the length of a welding line; extracting a welding action interval with the length of the welding line being greater than th2, calculating first-order differential values of all current points in the welding line, and when the first-order differential values are smaller than a preset threshold value th3, representing that the welding line is relatively stable, and reserving two corresponding current values;
s2.2, judging the number of the current points of the reserved stable section; when the number of the current points in the stable section is greater than a preset threshold th4, representing that the welding seam is a stable long welding seam, and reserving all the current points; otherwise, representing that the welding seam is a spot welding seam;
and S2.3, after removing abnormal values from the finally extracted stable long weld joint, calculating a current average value, namely the current stable value.
Further, the clustering method in the step S3 is as follows:
s3.1, performing density clustering on the current average value of each section of welding seam by adopting a DBSCAN method; when the number of the welding seam current points is smaller than 20, directly calculating the average value of the welding seam current average value, and not clustering; when the number m of the welding line current points is more than or equal to 20 and less than or equal to 120, setting min_samples=15; when the number of the current points is 120 < m < 250, setting min_samples=20; when the number m of the current points is more than or equal to 250, setting min_samples=30; setting a parameter eps=5, and clustering;
s3.2, when all the clustering labels are-1, representing that all the current average values cannot be clustered into one type; at the moment, filtering abnormal values of all current average values through a box graph method, and calculating the average value to be used as a current quality judgment basis;
when the clustering labels are not all-1, eliminating the current average value of which the label is-1, calculating the average value of the current average values of the rest clustering results according to the types, and when the average value result corresponding to each type is lower than a preset threshold value th5, representing that the current average value of the type is in a significantly low level and does not belong to normal welding current.
Compared with the prior art, the technical scheme adopted by the invention has the following beneficial effects:
(1) According to the steady-state current calculation method for the welding process, provided by the invention, the current condition during actual welding is analyzed, the independent spot welding and continuous spot welding conditions are filtered, the screened long weld joint is used as the calculation basis of the steady-state current, and compared with the traditional method for capturing the current and calculating the mean value, the judgment of the current quality is more accurate, so that the condition that the effective value calculated by the traditional method is lower can be effectively solved.
(2) According to the invention, the stable long welding seams are screened, the current stable values of the welding seams are calculated, clustering is further carried out, the current average value in a period of time is further calculated based on the clustering result, the current average value of each type of clustering result is used as a judgment basis of current quality, and the current average value is compared with the current range in the welding technological procedure, so that whether the current welding current meets the WPS requirement can be effectively judged, and a direct basis is provided for judging whether the welding current exceeds the limit.
Drawings
FIG. 1 is a flow chart of a welding steady-state current calculation method provided by the invention;
FIG. 2 is a graph of weld current in the presence of continuous spot welds provided in example 1 of the present invention;
FIG. 3 is a graph showing the effective current values calculated by the conventional method in example 1 of the present invention;
FIG. 4 is a graph of clustering results obtained by the method provided by the invention in embodiment 1 of the invention;
FIG. 5 is a graph of actual welding current conditions provided in example 2 of the present invention;
FIG. 6 is a graph showing the effective current values calculated by the conventional method in example 2 of the present invention;
fig. 7 is a graph of clustering results obtained by the method provided by the invention in embodiment 2 of the invention.
Description of the embodiments
The invention is further explained below with reference to the drawings.
The invention provides a steady-state current calculation method in a welding process, which comprises the following specific steps of:
s1, collecting current data in the operation process of the welding machine in real time through a current sensor, and judging a starting current point and an ending current point of each welding process.
Firstly, extracting all current point sequences with current greater than a threshold value th1, and eliminating non-arcing points and other interference points in the current sequences. In this embodiment, th1=5a, and all points with current values not greater than 5A are determined to be non-arcing points, and then are removed. Then, the first current point in the current point sequence is used as a starting point of a welding action, the rest current point sequence is traversed, a blank current point exists between the current point and the next current point (namely, a rejected current point exists), the current welding action is considered to be finished, the previous current point is used as an ending point of the previous welding action, and the next current point is used as a starting point of the next welding action. Repeating the above operations, a plurality of current intervals representing a plurality of welding actions may be obtained.
And S2, filtering the independent spot welding and the continuous spot welding, reserving a stable long welding line, and calculating a current stable value.
And traversing each welding action interval, and setting a preset threshold th2 of the length of the welding line. And extracting a welding action interval with the length of the welding line being greater than th2, calculating first-order differential values of all current points in the welding line, and when the first-order differential values are smaller than a preset threshold value th3, representing that the welding line is relatively stable, and reserving two corresponding current values. In this embodiment, th2=5 is set, i.e. when more than 5 current points are included in a section of the weld, the weld is considered to be a long weld. Setting th3=10, calculating the first order difference of two adjacent current values, judging whether current mutation occurs or not, and screening the current points of the stable section.
And further judging the number of the reserved current points of the stable section, wherein when the number of the current points of the stable section is greater than a preset threshold th4, the current points of the stable section are reserved, and if not, the welding line is a spot welding line. And removing abnormal values from the finally extracted long weld current points of the stable section, and calculating a current average value.
And S3, clustering the current average value of each section of welding seam obtained in the step S2, and further calculating the current average value in the period of time based on a clustering result.
In the embodiment, a DBSCAN method is adopted to perform density clustering on the current average value of each section of welding seam. The parameter eps=5 is set. When the number of the current points is smaller than 20, the average value of the current average values of all welding seams is directly calculated, and clustering is not performed. When the number of the current points is more than or equal to 20 and less than or equal to 120, setting min_samples=15; when the number of the current points is 120 < m < 250, setting min_samples=20; when the number m of current points is more than or equal to 250, min_samples=30 is set. Density clustering was performed based on the above settings, obtaining the following results:
when all the clustering labels are-1, the clustering labels represent that all the current average values cannot be clustered into one type; at the moment, the abnormal value filtering is carried out on all the current average values through a box graph method, and the average value is calculated and used as the current quality judgment basis.
When the clustering label is not-1, eliminating the current average value of which the label is-1, calculating the average value of the current average values of the rest clustering results according to the types, and when the average value result corresponding to each type is lower than a preset threshold value th5, representing that the current average value is in a significantly low level and does not belong to normal welding current. Th5 is set to 50A in this embodiment. And finally, reserving the average value of each class of current average value set as a current quality judgment basis.
And S4, comparing the current average value of each clustering result with the current range in the welding technological specification WPS, and judging whether the average current is in a reasonable WPS range.
The average value of the current average value calculated in each type of clustering result represents the average current of a process, and each current average value point in the process is the stable current value of a long welding line. Therefore, the current quality judgment basis can be carried out by comparing the welding technological regulations WPS.
In the actual robot welding process, when a certain process has a plurality of continuous spot welds, a plurality of over-low currents exist in the current values acquired every second, the effective value is lower when the current effective value is calculated wholly, and the erroneous judgment process of lower current quality can exist when the welding current value in the original normal range is calculated wholly. The calculation method provided by the invention can effectively solve the problem of inaccurate judgment of the effective value of the current. Two specific examples are provided below for verification.
Examples
As shown in fig. 2, in the case of continuous spot welding, a current point with a current greater than 5A is taken, an average value is taken as a current effective value, as shown in fig. 3, a calculation result is 35A, a calculation result based on the clustering method of the invention is shown in fig. 4, the clustering result comprises 30A and 70A, wherein 30A is a obviously unreasonable current, and if the current effective value in the period is discarded, the current effective value in the period should be 70A.
Examples
As shown in FIG. 5, the average value of the current points with the current greater than 5A is calculated, the result is 101.7A as shown in FIG. 6, the result of the clustering method based on the invention is 146.82A as shown in FIG. 7. It is obvious that the clustering result provided by the invention is more in line with the actual welding condition. The calculated effective value of the welding current is more valuable and can be used as the basis of current quality detection.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (3)
1. The steady-state current calculation method for the welding process is characterized by comprising the following steps of:
step S1, collecting current data in the running process of a welding machine in real time based on a current sensor, and capturing a starting current point and an ending current point of each welding action;
s2, filtering the conditions of independent spot welding and continuous spot welding, screening a long welding line, and calculating the current stable value of the long welding line; in particular, the method comprises the steps of,
step S2.1, traversing each welding action interval, and setting a preset threshold th2 of the length of a welding line; extracting a welding action interval with the length of the welding line being greater than th2, calculating first-order differential values of all current points in the welding line, and when the first-order differential values are smaller than a preset threshold value th3, representing that the welding line is relatively stable, and reserving two corresponding current values;
s2.2, judging the number of the current points of the reserved stable section; when the number of the current points in the stable section is greater than a preset threshold th4, representing that the welding seam is a stable long welding seam, and reserving all the current points; otherwise, representing that the welding seam is a spot welding seam;
s2.3, after removing abnormal values from the finally extracted stable long weld joint, calculating a current average value, namely a current stable value;
step S3, clustering the current stable values of the long weld joints obtained in the step S2, and calculating a current average value in a preset time period based on a clustering result;
and S4, comparing the current average value of each type of clustering result with the current range in the welding technological specification WPS, and judging the current quality.
2. The method for calculating steady-state current of a welding process according to claim 1, wherein the method for capturing the starting current point and the ending current point of the welding process in step S1 comprises:
s1.1, extracting all current point sequences with current greater than a threshold value th1, and eliminating non-arcing points and other interference points in the current sequences;
step S1.2, taking a first current point in the current point sequence as a starting point of a welding action, traversing the rest current point sequence, and considering that the current welding action is finished when a blank current point exists between the current point and the rear current point; taking the former current point as the ending point of the previous welding action, and taking the latter current point as the starting point of the next welding action;
and S1.3, repeating the steps to obtain a plurality of current intervals representing a plurality of welding actions.
3. The method for calculating steady-state current in a welding process according to claim 1, wherein the clustering method in step S3 is as follows:
s3.1, performing density clustering on the current average value of each section of welding seam by adopting a DBSCAN method; when the number of the welding seam current points is smaller than 20, directly calculating the average value of the welding seam current average value, and not clustering; when the number m of the welding line current points is more than or equal to 20 and less than or equal to 120, setting min_samples=15; when the number of the current points is 120 < m < 250, setting min_samples=20; when the number m of the current points is more than or equal to 250, setting min_samples=30; setting a parameter eps=5, and clustering;
s3.2, when all the clustering labels are-1, representing that all the current average values cannot be clustered into one type; at the moment, filtering abnormal values of all current average values through a box graph method, and calculating the average value to be used as a current quality judgment basis;
when the clustering labels are not all-1, eliminating the current average value of which the label is-1, calculating the average value of the current average values of the rest clustering results according to the types, and when the average value result corresponding to each type is lower than a preset threshold value th5, representing that the current average value of the type is in a significantly low level and does not belong to normal welding current.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310701879.1A CN116451045B (en) | 2023-06-14 | 2023-06-14 | Welding process steady-state current calculation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310701879.1A CN116451045B (en) | 2023-06-14 | 2023-06-14 | Welding process steady-state current calculation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116451045A CN116451045A (en) | 2023-07-18 |
CN116451045B true CN116451045B (en) | 2023-08-22 |
Family
ID=87127663
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310701879.1A Active CN116451045B (en) | 2023-06-14 | 2023-06-14 | Welding process steady-state current calculation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116451045B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116727914A (en) * | 2023-08-11 | 2023-09-12 | 苏芯物联技术(南京)有限公司 | Real-time intelligent control method for welding shielding gas under short welding seam scene |
CN117884817B (en) * | 2024-03-18 | 2024-05-10 | 苏芯物联技术(南京)有限公司 | Intelligent identification method for welding current process interval |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1990009857A1 (en) * | 1989-02-28 | 1990-09-07 | Mitsubishi Denki Kabushiki Kaisha | Pulse welding apparatus |
US5662820A (en) * | 1995-03-14 | 1997-09-02 | Trw Inc. | Welding process for drawn ARC stud welding |
CN2298902Y (en) * | 1997-08-25 | 1998-12-02 | 陆景云 | A. C. manually arc-welding thin plate welder controlled by microcomputer |
CN104526128A (en) * | 2014-11-27 | 2015-04-22 | 芜湖中集瑞江汽车有限公司 | Tungsten electrode inert gas shielded welding process of aluminum plate |
CN105081526A (en) * | 2014-05-08 | 2015-11-25 | 上海振华重工(集团)股份有限公司 | Liner-free inside welding method and device for pile leg |
CN106181043A (en) * | 2016-09-22 | 2016-12-07 | 哈尔滨工业大学 | A kind of welding method improving hybrid Laser-Arc Welding process stability |
CN109604767A (en) * | 2019-01-30 | 2019-04-12 | 浙江师范大学 | Intelligent welding control system and method for slab narrow gap GMA robot |
CN111932572A (en) * | 2020-10-12 | 2020-11-13 | 南京知谱光电科技有限公司 | Aluminum alloy molten pool contour extraction method |
CN114330491A (en) * | 2021-11-24 | 2022-04-12 | 东风汽车集团股份有限公司 | Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve |
CN114354639A (en) * | 2022-03-21 | 2022-04-15 | 苏芯物联技术(南京)有限公司 | Weld defect real-time detection method and system based on 3D point cloud |
CN115647535A (en) * | 2022-11-14 | 2023-01-31 | 北京北方车辆集团有限公司 | Double-side double-arc welding method for complex curved surface component of special vehicle |
CN116000496A (en) * | 2023-02-21 | 2023-04-25 | 洛阳船舶材料研究所(中国船舶集团有限公司第七二五研究所) | Large-thickness alloy vacuum electron beam welding joint and method |
CN116214009A (en) * | 2023-04-28 | 2023-06-06 | 苏芯物联技术(南京)有限公司 | Gas flow rate control method based on welding state identification |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2686128B1 (en) * | 2011-03-14 | 2017-05-10 | Illinois Tool Works Inc. | Method and apparatus to maintain welding current to compensate for deterioration of welding contact tip |
US10391582B2 (en) * | 2011-07-21 | 2019-08-27 | Ford Global Technologies, Llc | System and method of welding a workpiece |
-
2023
- 2023-06-14 CN CN202310701879.1A patent/CN116451045B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1990009857A1 (en) * | 1989-02-28 | 1990-09-07 | Mitsubishi Denki Kabushiki Kaisha | Pulse welding apparatus |
US5662820A (en) * | 1995-03-14 | 1997-09-02 | Trw Inc. | Welding process for drawn ARC stud welding |
CN2298902Y (en) * | 1997-08-25 | 1998-12-02 | 陆景云 | A. C. manually arc-welding thin plate welder controlled by microcomputer |
CN105081526A (en) * | 2014-05-08 | 2015-11-25 | 上海振华重工(集团)股份有限公司 | Liner-free inside welding method and device for pile leg |
CN104526128A (en) * | 2014-11-27 | 2015-04-22 | 芜湖中集瑞江汽车有限公司 | Tungsten electrode inert gas shielded welding process of aluminum plate |
CN106181043A (en) * | 2016-09-22 | 2016-12-07 | 哈尔滨工业大学 | A kind of welding method improving hybrid Laser-Arc Welding process stability |
CN109604767A (en) * | 2019-01-30 | 2019-04-12 | 浙江师范大学 | Intelligent welding control system and method for slab narrow gap GMA robot |
CN111932572A (en) * | 2020-10-12 | 2020-11-13 | 南京知谱光电科技有限公司 | Aluminum alloy molten pool contour extraction method |
CN114330491A (en) * | 2021-11-24 | 2022-04-12 | 东风汽车集团股份有限公司 | Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve |
CN114354639A (en) * | 2022-03-21 | 2022-04-15 | 苏芯物联技术(南京)有限公司 | Weld defect real-time detection method and system based on 3D point cloud |
CN115647535A (en) * | 2022-11-14 | 2023-01-31 | 北京北方车辆集团有限公司 | Double-side double-arc welding method for complex curved surface component of special vehicle |
CN116000496A (en) * | 2023-02-21 | 2023-04-25 | 洛阳船舶材料研究所(中国船舶集团有限公司第七二五研究所) | Large-thickness alloy vacuum electron beam welding joint and method |
CN116214009A (en) * | 2023-04-28 | 2023-06-06 | 苏芯物联技术(南京)有限公司 | Gas flow rate control method based on welding state identification |
Non-Patent Citations (1)
Title |
---|
李志明.基于动态电阻的点焊质量在线分析研究.《中国优秀硕士学位论文全文数据库 工程科技I辑》.2014,(第04期),第B022-210页. * |
Also Published As
Publication number | Publication date |
---|---|
CN116451045A (en) | 2023-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116451045B (en) | Welding process steady-state current calculation method | |
CN116214009B (en) | Gas flow rate control method based on welding state identification | |
CA2931624A1 (en) | Systems and methods for event detection and diagnosis | |
CN101364106A (en) | Welding quality control system and method for resistance welding | |
CN116275643B (en) | Intelligent recognition method for execution condition of welding process | |
CN105302123B (en) | The monitoring method of on-line measurement data | |
CN108956041B (en) | Sintering machine air leakage fault online diagnosis method based on single-side detection method of frequency spectrum characteristics | |
CN109445422A (en) | A kind of chemical production equipment failure prediction method | |
CN114646665A (en) | Arc welding defect real-time detection method and system | |
CN117093461A (en) | Method, system, equipment and storage medium for time delay detection and analysis | |
CN113505657B (en) | Welding spot quality detection method and device | |
CN117650790A (en) | Welding shielding gas measurement data compression storage method based on intelligent recognition of working conditions | |
CN114330491A (en) | Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve | |
Summerville et al. | Process monitoring of resistance spot welding using the dynamic resistance signature | |
CN108759479B (en) | Sintering machine air leakage fault online diagnosis method based on blind source separation unilateral detection method | |
CN103210358B (en) | Intelligent visual when monitoring process parameter and/or equipment parameter | |
CN1204562A (en) | Method for detecting formation of necking down during molten drop short-circuit transfer | |
CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
CN108411342B (en) | Method and system for predicting electrode short circuit based on pseudo resistance | |
CN115255566A (en) | Welding deviation real-time intelligent detection method based on high-quality time domain characteristics | |
CN112039021B (en) | Transformer excitation inrush current identification method based on differential waveform parameters | |
CN113514724A (en) | Photovoltaic system and arc detection method and device thereof | |
CN107154947A (en) | Based on effectively frequently the exception of network traffic of stream feature is detected and sorting technique | |
Kulkarni et al. | Machine learning based classification of welded components | |
CN114266489A (en) | Method for automatically establishing spot welding quality on-line evaluation model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |