CN117773281B - Welding state bidirectional sliding re-detection method based on historical data supplementary transmission - Google Patents
Welding state bidirectional sliding re-detection method based on historical data supplementary transmission Download PDFInfo
- Publication number
- CN117773281B CN117773281B CN202410179069.9A CN202410179069A CN117773281B CN 117773281 B CN117773281 B CN 117773281B CN 202410179069 A CN202410179069 A CN 202410179069A CN 117773281 B CN117773281 B CN 117773281B
- Authority
- CN
- China
- Prior art keywords
- data
- welding state
- welding
- point
- sliding
- 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 117
- 230000005540 biological transmission Effects 0.000 title claims abstract description 38
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 230000002457 bidirectional effect Effects 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 239000013589 supplement Substances 0.000 claims abstract description 6
- 230000000295 complement effect Effects 0.000 claims description 16
- 238000010791 quenching Methods 0.000 claims description 13
- 230000000171 quenching effect Effects 0.000 claims description 13
- 230000008033 biological extinction Effects 0.000 claims description 6
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 abstract description 3
- 238000007405 data analysis Methods 0.000 description 4
- 101100421134 Schizosaccharomyces pombe (strain 972 / ATCC 24843) sle1 gene Proteins 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Arc Welding Control (AREA)
Abstract
The invention discloses a bidirectional sliding re-detection method for welding state based on historical data supplementary transmission, which belongs to the technical field of intelligent welding, wherein when an edge sensor network is abnormal, each sensor system records the welding state before supplementary transmission, simultaneously writes data into a local database, and after a subsequent network is recovered, the sensor recovers data transmission and supplements the historical data; then constructing a forward sliding window, starting sliding re-detection, performing welding state change based on a sliding re-detection result, then constructing a reverse sliding window, starting supplementary detection, finding out the nearest welding state change point in the front-stage data, and updating the subsequent welding state by taking the welding state change point as a reference; finally, the welding state updating based on the welding current data is completed by combining the welding state before the repair transmission; according to the method, the welding data at the network communication abnormal boundary is optimized and updated by the bidirectional sliding weight detection method, and the accuracy of welding state identification is further improved.
Description
Technical Field
The invention belongs to the technical field of intelligent welding, and particularly relates to a welding state bidirectional sliding re-detection method based on historical data supplementary transmission.
Background
In the current industrial welding process, data analysis is performed by collecting various time sequence data, including welding voltage, welding current, shielding gas flow rate, wire feeding speed and the like, so that a series of welding operation analysis such as welding state identification, welding quality detection, gas leakage detection and the like is a mature means. However, the welding status recognition is used as a basis for other downstream operations, and the accuracy of the welding status recognition directly influences the accuracy of subsequent data analysis. When the edge side sensing network is abnormal, the time sequence data can be temporarily stored in a local storage mode until the network is repaired and then is received again and synchronously transmitted. However, the lack of welding data in the actual operation process directly affects the recognition of the welding state, so a method for not affecting the recognition result of the welding state while carrying out data supplement transmission needs to be explored.
Disclosure of Invention
The invention aims to: aiming at the problems in the background art, the invention provides a welding state bidirectional sliding re-detection method based on historical data supplementary transmission, which is used for re-detecting the welding state by arranging a bidirectional sliding window on the basis of the supplementary transmission of welding data, and updating the state information of the original data to obtain a more accurate welding state identification result.
The technical scheme is as follows: a welding state bidirectional sliding re-detection method based on historical data supplementary transmission comprises the following steps:
Step S1, when an edge sensor network is abnormal, each sensor system writes data into a local database, after a subsequent network is recovered, the sensor recovers data transmission, and supplements historical data, and a time sequence index timestamp of the supplemented data point is recorded.
And S2, backfilling the historical data to be supplemented to the correct time sequence position according to the timestamp, and inquiring and recording the welding state before supplementing to be os.
S3, constructing a forward sliding window slide w1, starting sliding weight detection, and changing a welding state based on a sliding weight detection result;
Step S4, constructing a reverse sliding window slide w2, starting supplementary detection, finding out the nearest welding state change point in the front-stage data, and updating the welding state detected in the step S3 by taking the welding state change point as a reference;
And S5, combining the welding state os before the supplementary transmission to finish the welding state updating based on the welding current data.
Further, the specific method for detecting the sliding weight in step S3 includes:
Setting a forward sliding window slide w1, wherein the window length is n; taking a starting point of the complementary current data as a starting point, sliding a slide w1 forward along a time sequence to receive new data, and when the number of data points in a sliding window is smaller than 3, storing the current data in a forward sequence, and keeping a welding state os before the complementary transmission unchanged; and when the data point received by the slide w1 is equal to 3, judging the welding state, and updating the welding state in real time.
Further, a mode of searching a state change point is adopted to change the welding state; all current points between adjacent arc starting points and arc extinguishing points in the time sequence direction are in an arc starting state, and all current points between the arc extinguishing points and the next arc starting points are in an arc extinguishing state;
when the front n-1 current values in the sliding window are smaller than th1 and the nth current value is larger than or equal to th1, recording the welding state of the window as arcing, and recording the current points larger than or equal to th1 as arcing points;
when the front n-1 current values in the sliding window are all greater than or equal to th1 and the nth current value is smaller than th1, recording the welding state of the window as arc extinction, and recording the current point smaller than th1 as arc extinction point; wherein th1 is a preset threshold;
When the conditions are not met, no welding state change point is represented in the sliding window, the sliding window continues to slide at the moment, and the judgment is repeated every time a new current value is received until the total data length of the sliding window is more than or equal to the length +n of the complementary current data set, and all state change points are found out.
Further, a reverse sliding window slide w2 is set, the window length is n, the 2 nd current point in the complementary current data set is taken as a starting point, the slide w2 receives data in a reverse sliding mode along a time sequence, when the number of data points in the sliding window is smaller than 3, the current data is stored in a reverse mode, the welding state os before the complementary transmission is kept unchanged, and the welding state updating is finished; when the received data point in the slide w2 is equal to 3, performing welding state judgment until the nearest state change point is found, and updating all subsequent welding states by taking the state change point as a starting point.
Further, the updating the subsequent welding state specifically includes:
When the nearest state change point is an arcing point, all current points from the arcing point to the next quenching point are in an arcing state, and then the welding state is updated in sequence until the data transmission is completed; when the nearest state change point is an arc quenching point, all current points from the arc quenching point to the next arc starting point are arc quenching states, and then the welding states are updated in sequence until the data transmission is completed.
Compared with the prior art, the technical scheme adopted by the invention has the following beneficial effects:
Based on the time sequence characteristics of the welding data, the invention stores the sensing data in the local database when the network abnormality of the edge end occurs, continuously collects and uploads each sensing data in real time after the network is restored, and simultaneously, also carries out breakpoint continuous transmission on the data stored in the local database.
Drawings
FIG. 1 is a flow chart of a method for detecting a welding state bidirectional sliding weight based on historical data supplementary transmission;
fig. 2 is a schematic diagram of a welding status updating method according to the present invention.
Detailed Description
The invention provides a bidirectional sliding re-detection method of a welding state based on historical data supplement transmission, which aims at the problem that partial data is temporarily stopped to be uploaded after communication interruption occurs in an edge sensor system due to external reasons, and then the subsequent data analysis of welding state judgment and abnormal welding identification based on the received sensing data of a cloud end can have larger errors. The core principles of the present invention are further explained with reference to the drawings.
As shown in FIG. 1, the welding state bidirectional sliding weight detection method based on historical data complementary transmission comprises the following steps:
and S1, when the edge sensor network is abnormal, each sensor system writes data into a local database and waits for network recovery. When the subsequent network is recovered, the sensor recovers data transmission, supplements the historical data, and records the time sequence index timestamp of the supplemented data point.
In the welding process, the edge sensor network receives a plurality of sensing data including welding current, welding voltage, shielding gas flow rate and wire feeding speed and transmits the sensing data to the cloud platform in real time for subsequent data analysis, the sensing data are all time sequence data, and when the edge network is abnormal, the data are stored in a local database to wait for communication recovery. When the network is restored, new real-time data is uploaded synchronously, and additional historical data is needed to be additionally transferred.
Because of the strong time sequence of the welding sensing data and the fact that the welding state judgment depends on the welding time sequence data, when a certain section of data is absent, a large error may exist in the judgment of the welding state, and therefore the existing welding state judgment result needs to be further adjusted after the supplementing of the transmitted historical data is considered. The core technical scheme provided by the invention can effectively solve the problems.
And S2, backfilling the historical data to be supplemented to the correct time sequence position according to the timestamp, and inquiring and recording the welding state before supplementing to be os. In this embodiment, adjustment and judgment of the welding state are performed based on the welding current data of the supplementary transmission. os includes both an arcing and an arc quenching state. As shown in fig. 2, the complementary current data set is seg+, and is complementary to the original data sets seg1 and seg2 according to the time sequence position.
And S3, constructing a forward sliding window slide w1, starting sliding weight detection, and updating the welding state based on a sliding weight detection result.
A forward sliding window slide w1 is arranged, and the window length is n. N=3 is set in this embodiment. Taking a starting point of the complementary current data as a starting point, sliding a slide w1 forward along a time sequence to receive new data, and when the number of data points in a sliding window is smaller than 3, storing the current data in a forward sequence, and keeping a welding state os before the complementary transmission unchanged; and when the data point received by the slide w1 is equal to 3, judging the welding state, and updating the welding state in real time.
In the invention, the welding state judgment is carried out by adopting a mode of searching a state change point. All current points between adjacent arc starting points and arc extinguishing points in the time sequence direction are in an arc starting state, and all current points between the arc extinguishing points and the next arc starting points are in an arc extinguishing state.
When the first 2 current values in the sliding window are smaller than th1 and the third current value is larger than or equal to th1, recording the welding state of the window as arcing, and recording the first current point larger than or equal to th1 as an arcing point;
When the first 2 current values in the sliding window are all more than or equal to th1 and the third current value is less than th1, recording the welding state of the window as arc extinction, and recording the first current point which is less than th1 as an arc extinction point; where th1 is a preset threshold, and in this embodiment, th1 is set to 10A.
When the conditions are not met, no welding state change point (namely an arc starting point or an arc extinguishing point) is represented in the sliding window, the sliding window continuously slides, and each time a new current value is received, the judgment is repeated until the total data length of the sliding window is more than or equal to the length +n of the complementary current data set, and all state change points are found out.
And S4, setting a reverse sliding window slide w2, wherein the window length is n. In this embodiment, the length 2=3 is set. And taking the 2 nd current point in the supplementary transmission current data set as a starting point, sliding the slide w2 along the time sequence to reversely slide and receive data, and when the number of the data points in the sliding window is smaller than 3, storing the current data in a reverse order, keeping the welding state os before the supplementary transmission unchanged, and ending the welding state updating. When the received data point in the slide w2 is equal to 3, performing welding state judgment until the nearest state change point is found, and updating all subsequent welding states by taking the state change point as a starting point. When the nearest state change point is an arcing point, all current points from the arcing point to the next quenching point are in an arcing state, and then the welding state is updated in sequence until the data transmission is completed. When the nearest state change point is an arc quenching point, all current points from the arc quenching point to the next arc starting point are arc quenching states, and then the welding states are updated in sequence until the data transmission is completed.
And S5, updating the welding state of all current data in the seg1, seg+ and seg2 set by combining the welding state os before the current data is supplemented.
In order to connect the current data sets and the front and rear time sequence data, the invention ensures that the welding current state at the junction is updated in real time, and the forward sliding window and the reverse sliding window need to slide a part more, and execute corresponding welding state judgment, thereby completing fusion updating of the welding state while fusing the data.
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 bidirectional sliding re-detection method for the welding state based on the historical data supplementary transmission is characterized by comprising the following steps of:
Step S1, when an edge sensor network is abnormal, each sensor system writes data into a local database, after a subsequent network is recovered, the sensor recovers data transmission, supplements historical data, and records a time sequence index timestamp of the supplemented data point;
step S2, backfilling the historical data to be supplemented to the correct time sequence position according to the timestamp, and inquiring and recording the welding state before supplementing to be os;
s3, constructing a forward sliding window slide w1, starting sliding weight detection, and changing a welding state based on a sliding weight detection result; the sliding weight detection method comprises the following steps:
Setting a forward sliding window slide w1, wherein the window length is n; taking a starting point of the complementary current data as a starting point, sliding a slide w1 forward along a time sequence to receive new data, and when the number of data points in a sliding window is smaller than 3, storing the current data in a forward sequence, and keeping a welding state os before the complementary transmission unchanged; when the data point received by the slide w1 is equal to 3, judging the welding state, and updating the welding state in real time;
The welding state changing based on the sliding weight detection result specifically comprises the following steps:
Carrying out welding state change by adopting a mode of searching a state change point; all current points between adjacent arc starting points and arc extinguishing points in the time sequence direction are in an arc starting state, and all current points between the arc extinguishing points and the next arc starting points are in an arc extinguishing state;
when the front n-1 current values in the sliding window are smaller than th1 and the nth current value is larger than or equal to th1, recording the welding state of the window as arcing, and recording the current points larger than or equal to th1 as arcing points;
when the front n-1 current values in the sliding window are all greater than or equal to th1 and the nth current value is smaller than th1, recording the welding state of the window as arc extinction, and recording the current point smaller than th1 as arc extinction point; wherein th1 is a preset threshold;
When the conditions are not met, representing that no welding state change point exists in the sliding window, continuously sliding the sliding window, repeating the judgment every time a new current value is received until the total data length of the sliding window is more than or equal to the length +n of the complementary current data set, and finding out all state change points;
Step S4, constructing a reverse sliding window slide w2, starting supplementary detection, finding out the nearest welding state change point in the front-stage data, and updating the welding state detected in the step S3 by taking the welding state change point as a reference;
And S5, combining the welding state os before the supplementary transmission to finish the welding state updating based on the welding current data.
2. The method for detecting the bidirectional sliding weight of the welding state based on the supplementary transmission of the historical data according to claim 1, wherein the specific method for detecting the supplementary transmission in step S4 comprises the following steps:
Setting a reverse sliding window slide w2, wherein the window length is n, taking the 2 nd current point in the complementary current data set as a starting point, sliding the slide w2 along a time sequence reversely to receive data, and when the number of data points in the sliding window is smaller than 3, storing the current data in a reverse order, keeping the welding state os before the complementary transmission unchanged, and ending the welding state update; when the received data point in the slide w2 is equal to 3, performing welding state judgment until the nearest state change point is found, and updating all subsequent welding states by taking the state change point as a starting point.
3. The method for bidirectional sliding re-detection of welding status based on the supplementary transmission of historical data according to claim 2, wherein updating all subsequent welding statuses specifically comprises:
When the nearest state change point is an arcing point, all current points from the arcing point to the next quenching point are in an arcing state, and then the welding state is updated in sequence until the data transmission is completed; when the nearest state change point is an arc quenching point, all current points from the arc quenching point to the next arc starting point are arc quenching states, and then the welding states are updated in sequence until the data transmission is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179069.9A CN117773281B (en) | 2024-02-18 | 2024-02-18 | Welding state bidirectional sliding re-detection method based on historical data supplementary transmission |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410179069.9A CN117773281B (en) | 2024-02-18 | 2024-02-18 | Welding state bidirectional sliding re-detection method based on historical data supplementary transmission |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117773281A CN117773281A (en) | 2024-03-29 |
| CN117773281B true CN117773281B (en) | 2024-05-03 |
Family
ID=90391184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410179069.9A Active CN117773281B (en) | 2024-02-18 | 2024-02-18 | Welding state bidirectional sliding re-detection method based on historical data supplementary transmission |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117773281B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1640603A (en) * | 2004-01-17 | 2005-07-20 | 上海威特力焊接设备制造有限公司 | Welding machine output characteristic control method |
| CN102664950A (en) * | 2012-04-18 | 2012-09-12 | 唐山松下产业机器有限公司 | Data communication method between welding power sources and computers |
| CN107305372A (en) * | 2016-04-25 | 2017-10-31 | 韩磊 | The electric automobile energy monitoring of the remote monitoring of system for cloud computing framework and more draping |
| KR101970775B1 (en) * | 2018-11-29 | 2019-04-19 | 주식회사 성원기업 | Welding monitoring device and monitoring method |
| CN109834366A (en) * | 2017-11-28 | 2019-06-04 | 株式会社达谊恒 | The starting the arc adjusts device, welding system and starting the arc method of adjustment |
| KR20200009681A (en) * | 2018-07-19 | 2020-01-30 | 한국조선해양 주식회사 | System and method for welding monitoring |
| CN112731853A (en) * | 2021-02-01 | 2021-04-30 | 中国石油天然气集团公司 | Data acquisition transmission controller |
| WO2022238323A1 (en) * | 2021-05-10 | 2022-11-17 | Fronius International Gmbh | Welding device and welding method |
| CN116441674A (en) * | 2023-06-14 | 2023-07-18 | 苏芯物联技术(南京)有限公司 | High-precision welding airflow control system and control method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CH696253A5 (en) * | 2000-12-29 | 2007-02-28 | Sticht Fertigungstech Stiwa | Plant Betriebsleiteinrichtung for manufacturing and / or mounting device. |
-
2024
- 2024-02-18 CN CN202410179069.9A patent/CN117773281B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1640603A (en) * | 2004-01-17 | 2005-07-20 | 上海威特力焊接设备制造有限公司 | Welding machine output characteristic control method |
| CN102664950A (en) * | 2012-04-18 | 2012-09-12 | 唐山松下产业机器有限公司 | Data communication method between welding power sources and computers |
| WO2013155935A1 (en) * | 2012-04-18 | 2013-10-24 | 唐山松下产业机器有限公司 | Method for performing data communication between welding power source and computer |
| CN107305372A (en) * | 2016-04-25 | 2017-10-31 | 韩磊 | The electric automobile energy monitoring of the remote monitoring of system for cloud computing framework and more draping |
| CN109834366A (en) * | 2017-11-28 | 2019-06-04 | 株式会社达谊恒 | The starting the arc adjusts device, welding system and starting the arc method of adjustment |
| KR20200009681A (en) * | 2018-07-19 | 2020-01-30 | 한국조선해양 주식회사 | System and method for welding monitoring |
| KR101970775B1 (en) * | 2018-11-29 | 2019-04-19 | 주식회사 성원기업 | Welding monitoring device and monitoring method |
| CN112731853A (en) * | 2021-02-01 | 2021-04-30 | 中国石油天然气集团公司 | Data acquisition transmission controller |
| WO2022238323A1 (en) * | 2021-05-10 | 2022-11-17 | Fronius International Gmbh | Welding device and welding method |
| CN116441674A (en) * | 2023-06-14 | 2023-07-18 | 苏芯物联技术(南京)有限公司 | High-precision welding airflow control system and control method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117773281A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110850711A (en) | Auxiliary driving control system and method based on cloud | |
| CN117773281B (en) | Welding state bidirectional sliding re-detection method based on historical data supplementary transmission | |
| CN115796610A (en) | Comprehensive monitoring method and system for operation of branch pipe forming system and storage medium | |
| CN106155035A (en) | Method for diagnosing faults based on maintenance class data and fault diagnosis system | |
| CN114463329A (en) | Welding defect detection method and system based on image and time sequence data fusion | |
| CN107978147A (en) | A kind of two-way detection restorative procedure of traffic flow abnormal data based on KNN algorithms | |
| CN105930839B (en) | A kind of pillar of electrification rail contacting net bar intelligent identification Method | |
| CN103294773A (en) | Smart real-time rainfall data statistical method | |
| CN105046426A (en) | Database multiple-historical data table-based working condition information section reconstruction method | |
| CN114842394A (en) | Swin transform-based automatic identification method for surgical video flow | |
| CN114800049A (en) | Grating ruler processing operation signal error compensation system | |
| CN111130009B (en) | Method for determining running state of visual image equipment of power transmission line channel | |
| CN102553939A (en) | Method for recovering continuously treated line strip steel tracking system | |
| CN113780646A (en) | Intelligent cutting and sizing method for continuous casting billet | |
| CN107914736B (en) | System control mode judgment method for train blocking working condition in rail transit | |
| CN109861807A (en) | Logical channel alignment schemes and system under multi-channel mode | |
| CN116030464B (en) | Welding arcing state real-time detection method based on semantic segmentation | |
| CN114058833B (en) | Automatic continuous annealing furnace control method and system, computer readable storage medium and computer program product | |
| CN113218404A (en) | Road data error determination method, related method and device | |
| CN110298255A (en) | A kind of the identification matching process and system of video content | |
| CN112874586B (en) | Urban rail transit intelligent train timetable matching method and electronic equipment | |
| CN117539210B (en) | Tracking method integrating machine vision and process control | |
| CN115828165B (en) | New energy intelligent micro-grid data processing method and system | |
| CN105912978A (en) | Lane line detection and tracking method based on concurrent pipelines | |
| CN112091967B (en) | Off-line programming batch correction method for welding robot track |
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 |