CN116275643A - Intelligent recognition method for execution condition of welding process - Google Patents
Intelligent recognition method for execution condition of welding process Download PDFInfo
- Publication number
- CN116275643A CN116275643A CN202310053574.4A CN202310053574A CN116275643A CN 116275643 A CN116275643 A CN 116275643A CN 202310053574 A CN202310053574 A CN 202310053574A CN 116275643 A CN116275643 A CN 116275643A
- Authority
- CN
- China
- Prior art keywords
- current
- interval
- voltage
- intervals
- clustering
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 193
- 238000003466 welding Methods 0.000 title claims abstract description 83
- 230000004927 fusion Effects 0.000 claims abstract description 48
- 238000004140 cleaning Methods 0.000 claims abstract description 17
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007334 copolymerization reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 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
- B23K31/02—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 soldering or welding
-
- 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)
- Mechanical Engineering (AREA)
- Lining Or Joining Of Plastics Or The Like (AREA)
Abstract
The invention discloses an intelligent recognition method for the execution condition of a welding process, which is characterized in that the execution condition of the welding process is characterized by a plurality of sections of welding current intervals and corresponding voltage intervals, and then the welding current intervals are used as the evaluation basis of welding quality; firstly, collecting high-frequency data in the actual welding process, dividing working procedures, and extracting representative current and voltage of each working procedure; clustering is carried out based on the current data, and a preliminary current process interval is obtained; clustering the voltage data in each type of preliminary current process interval; then carrying out voltage fusion and current fusion to obtain a current fusion interval, carrying out current interval cleaning on the primary current process interval, and finally obtaining an accurate current interval and a corresponding voltage interval as the execution condition of the welding process; the invention is based on a clustering method, and current and voltage intervals existing when the actual welding process is executed are identified, and the subsequent evaluation of the welding process execution condition can be carried out according to the welding process specification WPS.
Description
Technical Field
The invention belongs to the technical field of intelligent welding, and particularly relates to an intelligent recognition method for the execution condition of a welding process.
Background
In the conventional manual welding process, the welding quality is generally determined by the welding level of the welder, which is an index based on subjective evaluation by the person. For the problem of improper operation of a welder in the actual welding process, for example, the welding current is increased by pursuing the welding speed, the current is over-limited, and the like, the welder cannot monitor well.
The execution condition of the welding process of a welder is used as an important index for describing the actual welding scene of the welder, and comprises current and voltage information during different welding procedures. The combination of the information can effectively reflect the working efficiency and the working quality of a welder, is used for replacing subjective welder level evaluation indexes, and is more convincing. The welding process execution condition of a welder is compared with the corresponding welding process specification WPS standard, so that whether the manual welding process is standard or not can be better reflected, and whether the current overruns or not and the like are caused. However, no mature research is available in the prior art on how to identify the execution of the welding process by the welder.
Disclosure of Invention
The invention aims to: aiming at the problems in the background art, the invention provides an intelligent recognition method for the execution condition of a welding process, which comprises the steps of obtaining representative current and voltage of each process through dividing the processes, then clustering current intervals through a clustering method, and clustering corresponding voltage intervals in each type of current interval. Then carrying out voltage fusion and current fusion; and finally, cleaning the current interval to obtain a plurality of current and voltage intervals, namely the welding process condition actually executed by a welder.
The technical scheme is as follows: an intelligent recognition method for the execution condition of a welding process comprises the following steps:
step S1, collecting high-frequency current and voltage data in an actual welding process, and respectively extracting corresponding current and voltage data samples during stable operation of each procedure according to the actual welding condition;
step S2, based on the representative current data of each procedure obtained in the step S1, arranging and clustering the representative current data according to the order from small to large to obtain a plurality of types of preliminary current process intervals;
step S3, aiming at each type of preliminary current process interval, acquiring all corresponding voltage data in the type of interval, and clustering after arranging the voltage data in a small-to-large order to acquire a plurality of types of voltage clustering intervals;
step S4, when the voltage clustering intervals corresponding to the two adjacent preliminary current process areas have intersection, taking the union of the two voltage clustering intervals as a voltage fusion interval, and extracting current data corresponding to all voltage data in the voltage fusion interval as a new current fusion interval; traversing all adjacent preliminary current process intervals to generate a new current fusion interval;
step S5, cleaning a current section of the preliminary current process section based on the current fusion section generated in the step S4; judging the current interval corresponding to the voltage clustering interval which does not perform voltage fusion in each preliminary current process interval, when the corresponding current interval is a subset of the original preliminary current process interval, replacing the original preliminary current process interval with a new corresponding current interval, otherwise, not cleaning; traversing all the preliminary current process intervals to finish the cleaning of the current intervals;
and S6, after the current interval cleaning is completed, a final current interval and a corresponding voltage interval are divided, namely, the final current interval and the corresponding voltage interval are used as evaluation criteria for the execution condition of the welding process.
Further, in the step S1, a current and voltage data sample corresponding to each process during stable operation is extracted, and the specific steps include:
s1.1, when the sampling frequency is greater than 1Hz, calculating a current average value in each second, taking out all the current average values greater than 1 as current data samples, and similarly obtaining corresponding voltage data samples;
step S1.2, performing procedure division according to the acquired current data sample, wherein the specific rules are as follows: traversing indexes corresponding to all current data sample points, and when the difference between the index of the ith current data sample and the index of the (i+1) th current data sample is greater than 1, considering that the current has a discontinuous condition, and taking the ith current data sample as a boundary to split the working procedure;
step S1.3, after each procedure is extracted, a spot welding procedure is filtered; counting the number of current data samples in each procedure, and filtering out the procedure when the number of samples is less than or equal to 3;
and S1.4, selecting the median of the current and the voltage of each process in each process after the filtration as the representative current and the representative voltage of the process.
Further, the preliminary current process interval acquiring method in step S2 includes: clustering by adopting a DBSCAN method, and filtering samples with a clustering result of-1; in particular, the method comprises the steps of,
step S2.1, splicing the current of each procedure, and sequencing according to the current;
s2.2, taking out the current after sequencing, and performing DBSCAN density clustering;
and S2.3, based on a DBSCAN clustering result, dividing the current data into a plurality of classes, filtering large-span samples which cannot be clustered, taking out the upper limit and the lower limit of the current data in each class, and rounding to obtain a preliminary current process interval.
Further, in the step S3, a DBSCAN algorithm is adopted to perform voltage interval clustering, and large-span samples which cannot be clustered are filtered.
Further, in the step S4, a union of voltage data clustering intervals is taken as a voltage fusion interval, current data corresponding to all voltage data of the voltage fusion interval are extracted, current noise filtering is performed through DBSCAN, all current noise is filtered, and finally a current fusion interval corresponding to the voltage fusion interval is obtained; and traversing all adjacent preliminary current process intervals to obtain a current fusion interval.
Compared with the prior art, the technical scheme adopted by the invention has the following beneficial effects:
(1) The invention provides an intelligent recognition method for the execution condition of a welding process, which characterizes the execution condition of the welding process of a welder into a plurality of welding current intervals and corresponding voltage intervals. Acquiring current and voltage data in the manual welding process, acquiring a preliminary current process interval through clustering, and acquiring a current fusion interval through fusion; and the current interval is cleaned, so that more accurate current interval division can be obtained. Finally, a plurality of accurate current intervals and corresponding voltage intervals are obtained, so that the actual welding process execution condition of a welder is represented. Based on the execution condition, the method can be compared with a welding process specification WPS to judge whether the problems of current overrun and the like exist, and further data support is provided for evaluation of the welding level of a welder.
(2) When the high-frequency current and voltage samples are processed, the working procedures are firstly divided, the spot welding working procedures are filtered, the median of the current and the voltage of each working procedure is finally selected as the representative current and the representative voltage of the working procedure, the samples are clustered, and the relevant data during stable welding is selected for evaluation, so that the welding process execution condition of a welder can be better represented.
(3) When the current intervals are clustered, the problem that the current process intervals are not accurately divided under the condition of traditional single clustering is avoided, voltage clustering is further introduced on the basis of clustering the current intervals, the current fusion intervals are further obtained through the voltage fusion intervals, after the initial current process intervals are subjected to current interval cleaning, the current fusion intervals are combined to form more accurate current interval classification, and more accurate welding process execution conditions are formed together with the voltage classification intervals.
Drawings
FIG. 1 is a flow chart of an intelligent recognition method for the execution condition of a welding process;
FIG. 2 is a graph of clustering cases of preliminary current process intervals in an embodiment of the invention;
FIG. 3 is a graph of voltage clustering results corresponding to a first type of preliminary current process interval in an embodiment of the present invention;
FIG. 4 is a graph of voltage clustering results corresponding to a second type of preliminary current process interval in an embodiment of the present invention;
FIG. 5 is a voltage clustering result diagram corresponding to a third type of preliminary current process interval in an embodiment of the present invention;
FIG. 6 is a schematic diagram of the result of the current fusion interval in the embodiment of the invention.
Description of the embodiments
The invention is further explained below with reference to the drawings.
In the existing manual welding process, the quality of workpieces welded by different welding workers is uneven. The traditional factory still remains in the subjective experience level of workman to welding process's execution, can not carry out the intuitive judgement to welding workman's welding level. Because of improper operation of welders, the problems of current overrun and the like may exist in the actual manual welding process, and effective evaluation indexes are lacking when the welders are examined. Aiming at the problems, the invention aims to provide an intelligent recognition method for the execution condition of a welding process, which is characterized in that the actual welding data of a welder in the actual welding process is acquired, the process execution condition of the welder is not required to be monitored manually, the actual execution process condition of the welder is acquired only by acquiring high-frequency time sequence data in the welding process, a clustering method is adopted to recognize the current and voltage interval existing in the actual process execution, and further the welding process execution condition is evaluated according to the welding process specification WPS, so that a basis is provided for the assessment of the welder. As shown in fig. 1:
an intelligent recognition method for the execution condition of a welding process comprises the following steps:
and S1, collecting high-frequency current and voltage data in the actual welding process, and respectively extracting corresponding current and voltage data samples during stable operation of each procedure according to the actual welding condition. In particular, the method comprises the steps of,
s1.1, when the sampling frequency is higher, calculating a current average value in each second, taking out all the current average values which are larger than 1 as current data samples, and similarly obtaining corresponding voltage data samples;
step S1.2, performing procedure division according to the acquired current data sample, wherein the specific rules are as follows: traversing indexes corresponding to all current data sample points, and when the difference between the index of the ith current data sample and the index of the (i+1) th current data sample is greater than 1, considering that the current has a discontinuous condition, and splitting the process by taking the ith current data sample as a boundary. It should be noted that, the current data samples are used as a time sequence set of a plurality of current average values, and the index thereof has the following meaning: "sequential position of the current mean in the set";
step S1.3, after each procedure is extracted, a spot welding procedure is filtered; counting the number of current data samples in each process, and filtering out the process when the number of the samples is less than or equal to 3. Because the spot welding exists in the actual welding process, the welding is performed in a short time, and the current and the voltage of the welding have no universal reference value, so that the process identification is not performed.
And S1.4, selecting the median of the current and the voltage of each process in each process after the filtration as the representative current and the representative voltage of the process. The purpose of this step is to select the current and voltage at a relatively smooth stage in the process, representing the welding situation for this process. In actual welding, one procedure comprises an arc starting section, a stable section and an arc extinguishing section, relevant data when the welding is stable is selected for evaluation by detecting the process execution condition of a welder, and other phases do not have reference value.
Step S2, based on the representative current data of each procedure obtained in the step S1, arranging the representative current data in a sequence from small to large; and clustering is performed. In this embodiment, a DBSCAN method is used for clustering, and samples with a clustering result of-1 are filtered out.
And splicing the currents of each procedure, and sequencing according to the current.
Taking out the current after sequencing, and performing DBSCAN density clustering, wherein model parameters eps=5 and min_samples=30 are set
The final clustering result is-1, 0,1,2, 4 kinds in total. Where-1 represents a large span of samples that do not aggregate into a class, so the sample with a clustering result of-1 is filtered out.
The specific results are shown in FIG. 2, and the copolymerization is classified into 3 types in the examples. The upper limit and the lower limit of the current data in each class are taken out and rounded, and 3 classes of preliminary current process intervals can be obtained: [140,180],[180,250],[250,300].
And step S3, aiming at each type of preliminary current process interval, acquiring all corresponding voltage data in the type of interval, arranging the voltage data in a sequence from small to large, and clustering voltage data samples. In this embodiment, a DBSCAN algorithm is adopted, and samples with a clustering result of-1 are filtered out. The clustering method is the same here as in step S2.
For the first type of preliminary current process interval, the clustering result is shown in fig. 3, and the voltage data is copolymerized into 2 types: [22-25],[26,30]. Traversing all categories, and copolymerizing voltage data in a second category preliminary current process interval into 2 categories as shown in the clustering results in fig. 4-5: [26,29],[30,35]. Voltage data in the third type of preliminary current process interval is copolymerized into 3 types: [33,35],[37,39],[42,45].
And S4, clustering the voltage data in the step S3, wherein the intersection exists between the clustering results of the corresponding voltage data in the adjacent two types of preliminary current process intervals. Thus further current process interval fusion is required. In particular, the method comprises the steps of,
taking the union of voltage data clustering intervals as a voltage fusion interval, extracting current data corresponding to all voltage data of the voltage fusion interval, and performing current noise filtering through DBSCAN, namely filtering out samples with the clustering result of-1, and finally obtaining a current fusion interval corresponding to the voltage fusion interval; and traversing all adjacent preliminary current process intervals to obtain a current fusion interval.
In this embodiment, it can be seen that, in the first type of preliminary current process interval and the second type of preliminary current process interval, voltage data clustering intervals [26,30] and [26,29] have intersections, the two voltage intervals are combined to form [26,30], all current data corresponding to the voltage intervals are extracted, current noise point filtration is performed through a DBSCAN algorithm, and finally, the current fusion interval corresponding to the voltage fusion interval is determined to be [160,220]. Similarly, in the second type of preliminary current process interval and the third type of preliminary current process interval, voltage data clustering intervals [30,35] and [33,35] are intersected, the two voltage intervals are combined to form the union set [30,35], corresponding current data in the voltage intervals are extracted, current noise point filtration is carried out through a DBSCAN algorithm, and the current fusion interval corresponding to the voltage fusion interval [30,35] is determined to be [210,280], as shown in fig. 6.
Step S5, based on the current fusion section obtained in step S4, current section cleaning is carried out on the preliminary current process section obtained in step S2, and the purpose of current section cleaning is that after the voltage section is fused, the corresponding current fusion section and the original preliminary current process section possibly have intersection, so that in order to enable the current process section corresponding to the remaining unfused voltage section to be more accurate, the reserved current process section needs to be cleaned, and the current fusion section part corresponding to the voltage fusion section is removed. Specifically, judging a current interval corresponding to a voltage clustering interval which does not perform voltage fusion in each preliminary current process interval, when the corresponding current interval is a subset of the original preliminary current process interval, replacing the original preliminary current process interval with a new corresponding current interval, otherwise, not cleaning; and traversing all the preliminary current process intervals to finish the cleaning of the current intervals.
In this embodiment, taking the second type of preliminary current process section and the third type of preliminary current process section as examples, the first type of voltage section is removed in the third type of preliminary current process section, and the remaining voltage sections are cleaned and refined. The voltage intervals [37,39] are taken, the corresponding current intervals are [250,300], cleaning is not needed, the corresponding current intervals of the voltage intervals [42,45] are [250,300], and cleaning is also not needed.
Based on the method, the welding process conditions actually executed by the welding machine are finally divided into the following current-voltage intervals:
(1) Current interval: [140,180], voltage interval: [22,25]
(2) Current interval: [160,220], voltage interval: [26,30]
(3) Current interval: [210,280], voltage interval: [30,35]
(4) Current interval: [250,300], voltage interval: [37,39]
(5) Current interval: [250,300], voltage interval: [42,45].
Based on the identified execution condition of the welding process, the user can compare the execution condition with the corresponding current and voltage range in the welding process specification WPS, further evaluate the welding quality of a welder, and further find whether abnormal conditions such as current overrun exist.
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 (5)
1. The intelligent recognition method for the execution condition of the welding process is characterized by comprising the following steps of:
step S1, collecting high-frequency current and voltage data in an actual welding process, and respectively extracting corresponding current and voltage data samples during stable operation of each procedure according to the actual welding condition;
step S2, based on the representative current data of each procedure obtained in the step S1, arranging and clustering the representative current data according to the order from small to large to obtain a plurality of types of preliminary current process intervals;
step S3, aiming at each type of preliminary current process interval, acquiring all corresponding voltage data in the type of interval, and clustering after arranging the voltage data in a small-to-large order to acquire a plurality of types of voltage clustering intervals;
step S4, when the voltage clustering intervals corresponding to the two adjacent preliminary current process areas have intersection, taking the union of the two voltage clustering intervals as a voltage fusion interval, and extracting current data corresponding to all voltage data in the voltage fusion interval as a new current fusion interval; traversing all adjacent preliminary current process intervals to generate a new current fusion interval;
step S5, cleaning a current section of the preliminary current process section based on the current fusion section generated in the step S4; judging the current interval corresponding to the voltage clustering interval which does not perform voltage fusion in each preliminary current process interval, when the corresponding current interval is a subset of the original preliminary current process interval, replacing the original preliminary current process interval with a new corresponding current interval, otherwise, not cleaning; traversing all the preliminary current process intervals to finish the cleaning of the current intervals;
and S6, after the current interval cleaning is completed, a final current interval and a corresponding voltage interval are divided, namely, the final current interval and the corresponding voltage interval are used as evaluation criteria for the execution condition of the welding process.
2. The intelligent recognition method of the welding process execution condition according to claim 1, wherein the step S1 is to extract the corresponding current and voltage data samples during the steady operation of each procedure, and the specific steps include:
s1.1, when the sampling frequency is greater than 1Hz, calculating a current average value in each second, taking out all the current average values greater than 1 as current data samples, and similarly obtaining corresponding voltage data samples;
step S1.2, performing procedure division according to the acquired current data sample, wherein the specific rules are as follows: traversing indexes corresponding to all current data sample points, and when the difference between the index of the ith current data sample and the index of the (i+1) th current data sample is greater than 1, considering that the current has a discontinuous condition, and taking the ith current data sample as a boundary to split the working procedure;
step S1.3, after each procedure is extracted, a spot welding procedure is filtered; counting the number of current data samples in each procedure, and filtering out the procedure when the number of samples is less than or equal to 3;
and S1.4, selecting the median of the current and the voltage of each process in each process after the filtration as the representative current and the representative voltage of the process.
3. The intelligent recognition method of the welding process execution condition according to claim 1, wherein the preliminary current process interval obtaining method in step S2 includes: clustering by adopting a DBSCAN method, and filtering samples with a clustering result of-1; in particular, the method comprises the steps of,
step S2.1, splicing the current of each procedure, and sequencing according to the current;
s2.2, taking out the current after sequencing, and performing DBSCAN density clustering;
and S2.3, based on a DBSCAN clustering result, dividing the current data into a plurality of classes, filtering large-span samples which cannot be clustered, taking out the upper limit and the lower limit of the current data in each class, and rounding to obtain a preliminary current process interval.
4. The intelligent recognition method of the welding process execution condition according to claim 1, wherein in the step S3, a DBSCAN algorithm is adopted to cluster voltage intervals, and large-span samples which cannot be clustered are filtered.
5. The intelligent recognition method of the welding process execution condition according to claim 1, wherein in the step S4, a union of voltage data clustering intervals is taken as a voltage fusion interval, current data corresponding to all voltage data of the voltage fusion interval are extracted, current noise filtration is performed through DBSCAN, all current noise is filtered, and finally a current fusion interval corresponding to the voltage fusion interval is obtained; and traversing all adjacent preliminary current process intervals to obtain a current fusion interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310053574.4A CN116275643B (en) | 2023-02-03 | 2023-02-03 | Intelligent recognition method for execution condition of welding process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310053574.4A CN116275643B (en) | 2023-02-03 | 2023-02-03 | Intelligent recognition method for execution condition of welding process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116275643A true CN116275643A (en) | 2023-06-23 |
| CN116275643B CN116275643B (en) | 2023-11-07 |
Family
ID=86802184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310053574.4A Active CN116275643B (en) | 2023-02-03 | 2023-02-03 | Intelligent recognition method for execution condition of welding process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116275643B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117884816A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
| CN117884817A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Intelligent identification method for welding current process interval |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101559512A (en) * | 2009-05-21 | 2009-10-21 | 山东大学 | Welding track detection and control method of plate butt weld based on laser ranging |
| CN109093228A (en) * | 2018-09-25 | 2018-12-28 | 无锡三虹重工机械设备有限公司 | A kind of welding parameter intelligent monitor system |
| CN113762410A (en) * | 2021-09-17 | 2021-12-07 | 哈尔滨工业大学 | Key welding process parameter prediction method based on machine learning |
| CN115293303A (en) * | 2022-10-10 | 2022-11-04 | 广东电网有限责任公司中山供电局 | High-voltage transmission line network monitoring method, system, equipment and medium |
| US20220373999A1 (en) * | 2021-05-23 | 2022-11-24 | 3d Signals | Pattern Recognition for Part Manufacturing Processes |
| CN115570228A (en) * | 2022-11-22 | 2023-01-06 | 苏芯物联技术(南京)有限公司 | Intelligent feedback control method and system for welding pipeline gas supply |
-
2023
- 2023-02-03 CN CN202310053574.4A patent/CN116275643B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101559512A (en) * | 2009-05-21 | 2009-10-21 | 山东大学 | Welding track detection and control method of plate butt weld based on laser ranging |
| CN109093228A (en) * | 2018-09-25 | 2018-12-28 | 无锡三虹重工机械设备有限公司 | A kind of welding parameter intelligent monitor system |
| US20220373999A1 (en) * | 2021-05-23 | 2022-11-24 | 3d Signals | Pattern Recognition for Part Manufacturing Processes |
| CN113762410A (en) * | 2021-09-17 | 2021-12-07 | 哈尔滨工业大学 | Key welding process parameter prediction method based on machine learning |
| CN115293303A (en) * | 2022-10-10 | 2022-11-04 | 广东电网有限责任公司中山供电局 | High-voltage transmission line network monitoring method, system, equipment and medium |
| CN115570228A (en) * | 2022-11-22 | 2023-01-06 | 苏芯物联技术(南京)有限公司 | Intelligent feedback control method and system for welding pipeline gas supply |
Non-Patent Citations (3)
| Title |
|---|
| 张向文;华霖;蒋新标;周冬;: "基于离散制造业的焊接过程数据分析研究", 军民两用技术与产品, no. 01 * |
| 张鹏贤, 张宏杰, 马跃洲, 陈剑虹: "基于信号特征提取的电阻点焊质量在线评判", 焊接学报, no. 09 * |
| 陶亮;孙同景;段彬;张光先;: "基于粗集的焊接质量级别智能决策", 焊接学报, no. 07 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117884816A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
| CN117884817A (en) * | 2024-03-18 | 2024-04-16 | 苏芯物联技术(南京)有限公司 | Intelligent identification method for welding current process interval |
| 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 |
| CN117884816B (en) * | 2024-03-18 | 2024-05-17 | 苏芯物联技术(南京)有限公司 | Rapid process recommendation method based on historical welding current process interval |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116275643B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116275643B (en) | Intelligent recognition method for execution condition of welding process | |
| CN107145445B (en) | Automatic analysis method and system for error log of software automation test | |
| CN108108890B (en) | Process defect risk analysis method based on process incidence relation | |
| CN116451045B (en) | Welding process steady-state current calculation method | |
| CN111331211B (en) | On-line penetration detection method and system for electric spark small hole machining | |
| CN114083168B (en) | Welding spatter point identification method and system | |
| Saputra et al. | Quality improvement of molding machine through statistical process control in plastic industry | |
| CN114596061A (en) | Project data management method and system based on big data | |
| CN109710601A (en) | A kind of intelligence hydroelectric power plant operation data cleaning method | |
| CN105302123A (en) | Online data monitoring method | |
| CN115255566B (en) | Welding deviation real-time intelligent detection method based on high-quality time domain characteristics | |
| CN114330491A (en) | Method for optimizing quality of welding spot through analysis guidance of resistance spot welding curve | |
| CN110000705A (en) | A kind of detection method, system and the associated component of the operation of grinding machine abnormal processing | |
| CN116382224B (en) | Packaging equipment monitoring method and system based on data analysis | |
| CN113505657A (en) | Welding spot quality detection method and device | |
| CN117057942A (en) | Intelligent financial decision big data analysis system | |
| CN108648193B (en) | Biological tissue image identification method and system and computer storage medium thereof | |
| CN117884817B (en) | Intelligent identification method for welding current process interval | |
| CN115984576A (en) | Nondestructive burr removing method and system for square aluminum shell of new energy battery | |
| CN104504702A (en) | Cement notch pavement crack recognition method based on square lattice searching method | |
| CN113268419A (en) | Method, device, equipment and storage medium for generating test case optimization information | |
| CN113553659A (en) | System and method for fitting standard curve band of welding spot | |
| CN111881733A (en) | Worker operation step specification visual identification judgment and guidance method and system | |
| CN108089136B (en) | Automatic slicing method for fuel cell stack polarization curve test data | |
| CN117689999B (en) | Method and system for realizing TC4 tape coiling process optimization |
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 |