CN111250890B - Butt joint weld quality online monitoring method and device - Google Patents
Butt joint weld quality online monitoring method and device Download PDFInfo
- Publication number
- CN111250890B CN111250890B CN202010095731.4A CN202010095731A CN111250890B CN 111250890 B CN111250890 B CN 111250890B CN 202010095731 A CN202010095731 A CN 202010095731A CN 111250890 B CN111250890 B CN 111250890B
- Authority
- CN
- China
- Prior art keywords
- welding
- arc voltage
- current
- voltage data
- value
- 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
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
Abstract
The invention discloses a butt joint weld quality on-line monitoring method and a butt joint weld quality on-line monitoring device, wherein the method comprises the following steps: s1, collecting arc voltage data of the welding machine, and storing the arc voltage data which is unbiased to the center of the welding wire and the center of the welding line and has no defect in the welding line; s2, calculating the arc voltage data stored in the step S1 to obtain a reference static threshold value S; s3, collecting and storing the real-time arc voltage data of the current welding machine; s4, calculating the arc voltage data stored in the step S3 to obtain the current tnA dynamic threshold value d of the time; s5, weighting the dynamic threshold d and the static threshold S obtained in the steps S2 and S4 to obtain the current tnA final threshold value f at the moment; and S6, performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and comparing the sample exponential smoothing value y with the final threshold value f in a combined manner to judge whether the quality of the weld joint in progress is abnormal.
Description
[ technical field ] A method for producing a semiconductor device
The invention relates to the technical field of welding, in particular to a method and a device for monitoring the quality of a butt joint weld joint on line.
[ background of the invention ]
With the rapid development of the industrial manufacturing industry, welding has been widely applied in the fields of automobile and automobile part manufacturing industry, ships, machinery manufacturing, aerospace and the like, wherein a butt joint is the most adopted joint form in a welding structure, and welding automation and intellectualization have become the mainstream trend. In the actual welding process, there are some defective welds, which are disturbed by various factors, such as: cracks, incomplete penetration and fusion, slag inclusion, pores, appearance defects of welding seams and the like, so the method has important practical significance for monitoring the welding quality. The real-time monitoring of the welding seam quality can control and early warn the welding process, and avoid the loss caused by the loss of the welding quality monitoring to the large-scale production.
The arc welding process is a complex process with multiple factors interacting with each other, and when welding parameters or welding environment are changed, the welding quality is affected significantly. At present, the online monitoring of the weld quality of the butt joint is mainly carried out by judging by utilizing a static threshold or a dynamic threshold, intercepting a fixed window, taking an average value of window data and comparing the average value with the threshold, and if the average value exceeds the threshold, determining that the window data is abnormal, the method does not consider the validity of time sequence data, does not consider the data characteristics and generality of the weld, and does not monitor whether the welding environment is abnormal or whether the weld deviates or not, so that the integrity of the online monitoring of the weld quality is difficult to meet. Therefore, a new method needs to be designed to solve the problem.
[ summary of the invention ]
The invention provides a butt joint weld quality on-line monitoring method and a butt joint weld quality on-line monitoring device, which can better solve the problems existing in the weld quality on-line monitoring in the prior art.
The invention provides an online monitoring method for the quality of a butt joint weld joint, which comprises the following steps: s1, collecting arc voltage data of the welding machine, and storing the arc voltage data which is unbiased to the center of the welding wire and the center of the welding line and has no defect in the welding line; s2, calculating the arc voltage data stored in the step S1 to obtain a reference static threshold value S; s3, collecting and storing the real-time arc voltage data of the current welding machine; s4, calculating the arc voltage data stored in the step S3 to obtain the current tnA dynamic threshold value d of the time; s5, weighting the dynamic threshold d and the static threshold S obtained in the steps S2 and S4 to obtain the current tnA final threshold value f at the moment; and S6, performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and comparing the sample exponential smoothing value y with the final threshold value f in a combined manner to judge whether the quality of the weld joint in progress is abnormal.
In one embodiment, in step S6, the weld quality is determined to be abnormal if there is an increasing or decreasing trend in the continuous 6 points in the sampling point data.
In one embodiment, in step S1, welding current data of the welding machine is collected for use in verifying the arc voltage value; the collected and stored arc voltage data amount of the welding wire center and the welding seam center which are not deviated and have no defects of the welding seam is 100 to 300.
In one embodiment, in step S2, let the weld seam be any tnTime of day voltage data isCalculating the average value of each welding line respectivelyAnd standard deviation σiAnd then calculateAnd σiThe average value of (d) is obtained as a sample average value mu and a sample average standard deviation sigma, and a reference static threshold value s is obtained as [ mu-1.64 σ, [ mu +1.64 σ ]]。
In one embodiment, in step S4, n sampling points currently collected by the weld are sorted from large to small in time series, different weights are given to the corresponding n samples, and a weighted average of the samples is calculatedAnd standard deviation ofTo obtain tnDynamic threshold at time of day of
In one embodiment, in step S5, the current sampling point t is samplednWeighting the dynamic and static thresholds at the moment, setting the weight of the static threshold to be 0.8 and the weight of the dynamic threshold to be 0.2 by combining the generality of the reference static threshold and the dynamic characteristics of data per se, and determining that the current t is the current tnThe final threshold at the moment of time is
The invention also provides a butt joint weld quality on-line monitoring device, and the device uses the method, and comprises the following steps: the training system library module is used for acquiring arc voltage data of the welding machine and storing the arc voltage data which has no deviation between the center of the welding wire and the center of the welding line and has no defect in the welding line;
a static threshold calculation module for calculating a static thresholdCalculating arc voltage data stored in the training system library module to obtain a reference static threshold value s; the online electric parameter acquisition module is used for acquiring and storing real-time arc voltage data of the current welding machine; a dynamic threshold calculation module for calculating the arc voltage data stored in the on-line electrical parameter acquisition module to obtain the current tnA dynamic threshold value d of the time; an on-line weld quality monitoring module for weighting the dynamic threshold value d and the static threshold value s to obtain the current tnAnd performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and comparing the sample exponential smoothing value y with the final threshold value f to judge whether the quality of the ongoing welding seam is abnormal or not.
In one embodiment, the online weld quality monitoring module determines that the weld quality is abnormal when the online weld quality monitoring module detects that 6 continuous points in the sampling point data have an increasing or decreasing trend.
In one embodiment, the data acquisition in the training system library module is collected by the controller via a sensor.
In one embodiment, the training system library module collects arc voltage data of the welding machine in an offline manner.
According to the online monitoring method and device for the weld quality of the butt joint, dynamic threshold calculated by combining self time sequence data and reference data statistical threshold weighting are combined, exponential smoothing is used for a current point sequence instead of simple mean value comparison with the threshold, instability and importance of the current point are considered, and online monitoring precision is improved.
[ description of the drawings ]
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic flow chart of a butt joint weld quality on-line monitoring method;
fig. 2 is a schematic structural diagram of an online monitoring device for the weld quality of a butt joint corresponding to fig. 1.
[ detailed description ] embodiments
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Fig. 1 is a schematic flow chart of a butt joint weld quality online monitoring method, and fig. 2 is a schematic structural diagram of a butt joint weld quality online monitoring device corresponding to fig. 1, as shown in fig. 1 and fig. 2.
The embodiment provides an online monitoring device 100 for the weld quality of a butt joint, which comprises a training system library module 1, a static threshold calculation module 2, an online electrical parameter acquisition module 3, a dynamic threshold calculation module 4 and an online weld quality monitoring module 5, and corresponds to the below online monitoring method for the weld quality of a butt joint, as shown in fig. 2.
And the training system library module 1 is used for acquiring arc voltage data of the welding machine and storing the arc voltage data which has no deviation between the center of the welding wire and the center of the welding line and has no defect in the welding line. Data acquisition in the training system library module is collected by the controller via the sensors, and the training system library module preferably acquires arc voltage data of the welding machine via an offline mode.
And the static threshold calculation module 2 is used for calculating the arc voltage data stored in the training system library module to obtain a reference static threshold s.
And the on-line electric parameter acquisition module 3 is used for acquiring and storing real-time arc voltage data of the current welding machine.
A dynamic threshold calculation module 4 for calculating the arc voltage data stored in the on-line electrical parameter acquisition module to obtain the current tnDynamic threshold d of the moment.
An on-line weld quality monitoring module 5, configured to weight the dynamic threshold d and the static threshold s to obtain the current tnA final threshold value f of the moment, performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and combining the sample exponential smoothing value y and the final threshold value fAnd judging whether the quality of the weld joint in progress is abnormal or not. Preferably, when the on-line weld quality monitoring module monitors that 6 continuous points in the sampling point data have an increasing or decreasing trend, the on-line weld quality monitoring module judges that the weld quality is abnormal.
The online monitoring method for the weld quality of the butt joint in the embodiment can be applied to a welding machine or a robot, and comprises the following steps:
and step S1, collecting arc voltage data of the welding machine, and storing the arc voltage data which has no deviation between the center of the welding wire and the center of the welding seam and has no defect on the welding seam. Preferably, welding current data of the welding machine is collected for use in verifying the arc voltage value, i.e. for assisting in verifying the validity of the arc voltage value. Specifically, the PLC sensor can be used for collecting robot arc voltage and welding current data and storing data which is unbiased between the center of the welding wire and the center of a welding seam and has no defect in welding quality. The amount of the arc voltage data collected and stored is generally between 100 and 300, and 200 are selected in the embodiment.
In step S2, the arc voltage data stored in step S1 is calculated to obtain the reference static threshold S. Specifically, according to the 200 unbiased complete time series voltage data with no defect in welding quality obtained in step S1, the weld i or t is madenTime of day voltage data isCalculating the average value of each welding line respectivelyAnd standard deviation σiAnd then calculateAnd σiThe average of i-1, 2, …,200 yields the sample mean μ and the sample mean standard deviation σ, and yields the baseline static threshold s-1.64 σ, μ +1.64 σ, with 90% confidence]。
And step S3, acquiring and storing the real-time arc voltage data of the current welding machine. Specifically, arc voltage and welding current data of the current welding robot can be collected and collected in real time through the PLC sensor.
Step S4, calculating the arc voltage data stored in step S3 to obtain the current tnDynamic threshold d of the moment. Specifically, let weld i cut off to time t at the current sampling pointnN is 0,1,2, …, n sampling points are collected, n sampling points are sorted from large to small according to time sequence, different weights are given to the n samples, the closer to the current point, the higher the weight is, the sample weights of the n sampling points are respectively 0.80,0.81,0.82,…,0.8n-1Calculating a sample weighted averageAnd standard deviation ofGet t at 95% confidencenDynamic threshold at time of day of
Step S5, weighting the dynamic threshold d and the static threshold S obtained in steps S2 and S4 to obtain the current tnThe final threshold f at the moment. Specifically, the weld i is at the current sampling point tnThreshold value of time: for the weld joint i obtained in the steps 2) and 4) at the current sampling point tnWeighting the dynamic and static thresholds at the moment, setting the weight of the static threshold to be 0.8 and the weight of the dynamic threshold to be 0.2 by combining the generality of the reference static threshold and the dynamic characteristics of data per se, and determining that the current t is the current tnThe final time threshold is:
and step S6, performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and comparing the sample exponential smoothing value y with the final threshold value f in combination to judge whether the quality of the weld joint in progress is abnormal. Specifically, the weld i is at the current sampling point tnTime sample value: for cutoff to tnTime of dayThe ordinal number data are sequenced from large to small, and the sample weights of the n sampling points are respectively 0.6 in consideration of the instability and the timeliness of the current point0,0.61,0.62,…,0.6n-1Then the current sampling point tnTime sample dataThe samples are weighted averages.
Preferably, in step S6, if there is an increasing or decreasing trend in the continuous 6 points in the sampling point data, it is determined that the weld quality is abnormal. Specifically, the weld i is at the current sampling point tnQuality monitoring at the moment: if it isIf the current time is not within the interval S, the current time is considered to have abnormity and is reminded; if tnTime of day and first 5 voltage dataIf the number of the current time points is more than 0 or less than 0 and is 5, the current time point is considered to be abnormal and reminded; otherwise the data is considered normal.
From the above, the invention is an online monitoring method for the weld quality of the butt joint, which combines the dynamic threshold calculated by self time sequence data and the weighting of the reference data statistical threshold, and uses exponential smoothing instead of simple mean value comparison to the current point sequence with the threshold, thereby not only considering the instability of the current point, but also considering the importance of the current point. Except for the traditional method for judging the abnormality when the threshold value exceeds the upper and lower bounds, the method also increases the judgment that the abnormality is also judged if the continuous 6 points have the increasing or decreasing trend, and improves the accuracy of online monitoring.
The various embodiments described above and shown in the drawings are illustrative of the invention and are not exhaustive of the invention. Any modification of the present invention by a person of ordinary skill in the related art within the scope of the basic technical idea of the present invention is within the scope of the present invention.
Claims (10)
1. The butt joint weld quality on-line monitoring method is characterized by comprising the following steps of:
s1, collecting arc voltage data of the welding machine, and storing the arc voltage data which is unbiased to the center of the welding wire and the center of the welding line and has no defect in the welding line;
s2, calculating the arc voltage data stored in the step S1 to obtain a reference static threshold value S;
s3, collecting and storing the real-time arc voltage data of the current welding machine;
s4, calculating the arc voltage data stored in the step S3 to obtain the current tnA dynamic threshold value d of the time;
s5, weighting the dynamic threshold d and the static threshold S obtained in the steps S2 and S4 to obtain the current tnA final threshold value f at the moment;
s6, performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, and comparing the sample exponential smoothing value y with a final threshold value f to judge whether the weld quality in progress is abnormal or not, wherein if the sample exponential smoothing value y is larger than the final threshold value f, the weld quality is abnormal, and if the sample exponential smoothing value y is smaller than or equal to the final threshold value f, the weld quality is normal.
2. The method of claim 1, wherein:
in step S6, if there is an increasing or decreasing trend at 6 consecutive points in the sampling point data, it is determined that the weld quality is abnormal.
3. The method of claim 1, wherein:
collecting welding current data of the welding machine for verifying the arc voltage value in step S1;
the collected and stored arc voltage data amount of the welding wire center and the welding seam center which are not deviated and have no defects of the welding seam is 100 to 300.
4. The method of claim 1, wherein:
in the step ofIn S2, let the weld seam be tnTime of day voltage data isCalculating the average value of each welding line respectivelyAnd standard deviation σiAnd then calculateAnd σiThe average value of (d) is obtained as a sample average value mu and a sample average standard deviation sigma, and a reference static threshold value s is obtained as [ mu-1.64 σ, [ mu +1.64 σ ]]。
5. The method of claim 4, wherein:
in step S4, n sampling points currently collected by the weld are sorted from large to small according to a time sequence, different weights are given to the corresponding n samples, and a weighted average of the samples is calculatedAnd standard deviation ofTo obtain tnDynamic threshold at time of day of
6. The method of claim 5, wherein:
in step S5, the current sampling point t is samplednWeighting the dynamic and static thresholds at the moment, setting the weight of the static threshold to be 0.8 and the weight of the dynamic threshold to be 0.2 by combining the generality of the reference static threshold and the dynamic characteristics of data per se, and determining that the current t is the current tnThe final threshold at the moment of time is
7. An on-line monitoring device for the weld quality of a butt joint, which uses the method of any one of the preceding claims 1 to 6, comprising:
the training system library module is used for acquiring arc voltage data of the welding machine and storing the arc voltage data which has no deviation between the center of the welding wire and the center of the welding line and has no defect in the welding line;
the static threshold calculation module is used for calculating the arc voltage data stored in the training system library module to obtain a reference static threshold s;
the online electric parameter acquisition module is used for acquiring and storing real-time arc voltage data of the current welding machine;
a dynamic threshold calculation module for calculating the arc voltage data stored in the on-line electrical parameter acquisition module to obtain the current tnA dynamic threshold value d of the time;
an on-line weld quality monitoring module for weighting the dynamic threshold value d and the static threshold value s to obtain the current tnAnd performing exponential smoothing on the current sampling point to obtain a sample exponential smoothing value y, comparing the sample exponential smoothing value y with the final threshold value f in a combined manner to judge whether the quality of the weld seam in progress is abnormal, if the sample exponential smoothing value y is larger than the final threshold value f, indicating that the quality of the weld seam is abnormal, and if the sample exponential smoothing value y is smaller than or equal to the final threshold value f, indicating that the quality of the weld seam is normal.
8. The apparatus of claim 7, wherein:
and when the on-line welding seam quality monitoring module monitors that 6 continuous points in the sampling point data have an increasing or decreasing trend, the on-line welding seam quality monitoring module judges that the welding seam quality is abnormal.
9. The apparatus of claim 7, wherein:
and data acquisition in the training system library module is collected by the controller through a sensor.
10. The apparatus of claim 7, wherein:
the training system library module collects arc voltage data of the welding machine in a offline mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010095731.4A CN111250890B (en) | 2020-02-17 | 2020-02-17 | Butt joint weld quality online monitoring method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010095731.4A CN111250890B (en) | 2020-02-17 | 2020-02-17 | Butt joint weld quality online monitoring method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111250890A CN111250890A (en) | 2020-06-09 |
CN111250890B true CN111250890B (en) | 2021-11-23 |
Family
ID=70941589
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010095731.4A Active CN111250890B (en) | 2020-02-17 | 2020-02-17 | Butt joint weld quality online monitoring method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111250890B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111843272B (en) * | 2020-07-10 | 2022-02-22 | 中车工业研究院有限公司 | Quality discrimination method and device based on welding process information fusion |
CN112882996A (en) * | 2021-01-05 | 2021-06-01 | 唐山松下产业机器有限公司 | Welding data processing method, processing device and processing system |
CN113478056B (en) * | 2021-06-30 | 2022-11-04 | 武汉理工大学 | Novel real-time arc voltage tracking method for arc welding |
CN115255566B (en) * | 2022-09-26 | 2022-12-16 | 苏芯物联技术(南京)有限公司 | Welding deviation real-time intelligent detection method based on high-quality time domain characteristics |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1670648A (en) * | 2004-03-16 | 2005-09-21 | C.R.F.阿西安尼顾问公司 | A method for controlling the quality of industrial processes and system therefrom |
CN101977720A (en) * | 2009-05-22 | 2011-02-16 | C.R.F.阿西安尼顾问公司 | System for monitoring arc welding processes and corresponding monitoring method |
WO2012050108A1 (en) * | 2010-10-14 | 2012-04-19 | 住友金属工業株式会社 | Welding quality determination device |
CN102596476A (en) * | 2009-11-13 | 2012-07-18 | 林肯环球股份有限公司 | Method and apparatus for monitoring weld quality |
CN206241443U (en) * | 2016-11-24 | 2017-06-13 | 长沙学院 | Arc length control device |
KR20190061547A (en) * | 2017-11-28 | 2019-06-05 | 한양대학교 산학협력단 | Method for detecting pit defects and evaluating quality of weld zone, and system using the method |
-
2020
- 2020-02-17 CN CN202010095731.4A patent/CN111250890B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1670648A (en) * | 2004-03-16 | 2005-09-21 | C.R.F.阿西安尼顾问公司 | A method for controlling the quality of industrial processes and system therefrom |
CN101977720A (en) * | 2009-05-22 | 2011-02-16 | C.R.F.阿西安尼顾问公司 | System for monitoring arc welding processes and corresponding monitoring method |
CN102596476A (en) * | 2009-11-13 | 2012-07-18 | 林肯环球股份有限公司 | Method and apparatus for monitoring weld quality |
WO2012050108A1 (en) * | 2010-10-14 | 2012-04-19 | 住友金属工業株式会社 | Welding quality determination device |
CN206241443U (en) * | 2016-11-24 | 2017-06-13 | 长沙学院 | Arc length control device |
KR20190061547A (en) * | 2017-11-28 | 2019-06-05 | 한양대학교 산학협력단 | Method for detecting pit defects and evaluating quality of weld zone, and system using the method |
Also Published As
Publication number | Publication date |
---|---|
CN111250890A (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111250890B (en) | Butt joint weld quality online monitoring method and device | |
CN111047225B (en) | SMT surface mounting component welding spot quality evaluation method based on edge side model processing | |
CN113988202B (en) | Mechanical arm abnormal vibration detection method based on deep learning | |
US9015173B2 (en) | Spot weld data management and monitoring system | |
CN1766587A (en) | Real-time quality detection and alarm method for car body spot welding | |
CN109664009B (en) | Feedforward type resistance welding quality monitoring system and method | |
Summerville et al. | Nugget diameter in resistance spot welding: a comparison between a dynamic resistance based approach and ultrasound C-scan | |
JP2012076146A (en) | Device and method for determining quality of welding in real time | |
CN110597221A (en) | System and method for analyzing and predicting abnormal machine processing behavior | |
CN112091472B (en) | Welding process quality fusion judgment method and device | |
CN110909782A (en) | Method for diagnosing machine tool spindle fault based on multi-feature combined deep learning | |
CN109345060B (en) | Product quality characteristic error traceability analysis method based on multi-source perception | |
CN108388237B (en) | Fault diagnosis method, device, equipment and medium for discrete manufacturing equipment | |
CN113076817A (en) | Weld pore defect real-time detection method and system | |
CN112153150A (en) | Industrial site monitoring method suitable for industrial Internet | |
CN111178156A (en) | Time sequence characteristic effective window extraction method applied to machine learning | |
CN112630579A (en) | Aging test method and system for servo driver | |
Mayr et al. | In-line sensor-based process control of the calendering process for lithium-ion batteries | |
CN112686838A (en) | Rapid detection device and detection method for ship anchor chain flash welding system | |
CN110154027B (en) | Robot intelligent welding method based on cloud computing | |
KR101584421B1 (en) | Monitoring system for arc welding | |
JP2001353579A (en) | Device for judging acceptability or unacceptability of quality of welding | |
KR20190061547A (en) | Method for detecting pit defects and evaluating quality of weld zone, and system using the method | |
CN117396289A (en) | Method for additive manufacturing of a component | |
Breitenbach et al. | A Systematic Literature Review on Machine Learning Approaches for Quality Monitoring and Control Systems for Welding Processes |
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 |