Weld joint quality detection method based on Transform neural network
The invention discloses a weld joint quality detection method based on a Transform neural network, which comprises the following steps of: S1, additionally arranging a high-speed capacity molten pool monitoring camera at the end, close to a welding gun, of a welding manipulator, acquiring welding sh...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | MA CHENG WEI KAI ZHU XINYING GAO XIANGYU CHEN MIN SUN YULING LI CONGCONG WANG JIWEI LI JIAHUI ZHANG XUNBING SUN XUEBEI WANG BIN |
| description | The invention discloses a weld joint quality detection method based on a Transform neural network, which comprises the following steps of: S1, additionally arranging a high-speed capacity molten pool monitoring camera at the end, close to a welding gun, of a welding manipulator, acquiring welding shooting image data in real time, and monitoring the states of an electric arc, a molten pool, a groove and the like; s2, basic data enhancement is carried out on the acquired data, a multi-image overlapping enhancement method is used, and the detection efficiency of small targets such as welding seams is improved; s3, a visual Transform neural network welding seam recognition model based on self-attention is constructed; s4, visualizing the change of the training process of the model by adopting a multi-modal related attention method, and adjusting the structure of the model; and S5, detecting the quality of the welding seam by using the trained model. According to the method, the data has relatively high robustness |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114255220A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114255220A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114255220A3</originalsourceid><addsrcrecordid>eNrjZHANT81JUcjKz8wrUSgsTczJLKlUSEktSU0uyczPU8hNLcnIT1FISixOTVEA8kOKEvOK0_KLchXyUkuLEnOAVEl5flE2DwNrWmJOcSovlOZmUHRzDXH20E0tyI9PLS5ITE4Fqox39jM0NDEyNTUyMnA0JkYNAAhFM1o</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Weld joint quality detection method based on Transform neural network</title><source>esp@cenet</source><creator>MA CHENG ; WEI KAI ; ZHU XINYING ; GAO XIANGYU ; CHEN MIN ; SUN YULING ; LI CONGCONG ; WANG JIWEI ; LI JIAHUI ; ZHANG XUNBING ; SUN XUEBEI ; WANG BIN</creator><creatorcontrib>MA CHENG ; WEI KAI ; ZHU XINYING ; GAO XIANGYU ; CHEN MIN ; SUN YULING ; LI CONGCONG ; WANG JIWEI ; LI JIAHUI ; ZHANG XUNBING ; SUN XUEBEI ; WANG BIN</creatorcontrib><description>The invention discloses a weld joint quality detection method based on a Transform neural network, which comprises the following steps of: S1, additionally arranging a high-speed capacity molten pool monitoring camera at the end, close to a welding gun, of a welding manipulator, acquiring welding shooting image data in real time, and monitoring the states of an electric arc, a molten pool, a groove and the like; s2, basic data enhancement is carried out on the acquired data, a multi-image overlapping enhancement method is used, and the detection efficiency of small targets such as welding seams is improved; s3, a visual Transform neural network welding seam recognition model based on self-attention is constructed; s4, visualizing the change of the training process of the model by adopting a multi-modal related attention method, and adjusting the structure of the model; and S5, detecting the quality of the welding seam by using the trained model. According to the method, the data has relatively high robustness</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220329&DB=EPODOC&CC=CN&NR=114255220A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220329&DB=EPODOC&CC=CN&NR=114255220A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MA CHENG</creatorcontrib><creatorcontrib>WEI KAI</creatorcontrib><creatorcontrib>ZHU XINYING</creatorcontrib><creatorcontrib>GAO XIANGYU</creatorcontrib><creatorcontrib>CHEN MIN</creatorcontrib><creatorcontrib>SUN YULING</creatorcontrib><creatorcontrib>LI CONGCONG</creatorcontrib><creatorcontrib>WANG JIWEI</creatorcontrib><creatorcontrib>LI JIAHUI</creatorcontrib><creatorcontrib>ZHANG XUNBING</creatorcontrib><creatorcontrib>SUN XUEBEI</creatorcontrib><creatorcontrib>WANG BIN</creatorcontrib><title>Weld joint quality detection method based on Transform neural network</title><description>The invention discloses a weld joint quality detection method based on a Transform neural network, which comprises the following steps of: S1, additionally arranging a high-speed capacity molten pool monitoring camera at the end, close to a welding gun, of a welding manipulator, acquiring welding shooting image data in real time, and monitoring the states of an electric arc, a molten pool, a groove and the like; s2, basic data enhancement is carried out on the acquired data, a multi-image overlapping enhancement method is used, and the detection efficiency of small targets such as welding seams is improved; s3, a visual Transform neural network welding seam recognition model based on self-attention is constructed; s4, visualizing the change of the training process of the model by adopting a multi-modal related attention method, and adjusting the structure of the model; and S5, detecting the quality of the welding seam by using the trained model. According to the method, the data has relatively high robustness</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHANT81JUcjKz8wrUSgsTczJLKlUSEktSU0uyczPU8hNLcnIT1FISixOTVEA8kOKEvOK0_KLchXyUkuLEnOAVEl5flE2DwNrWmJOcSovlOZmUHRzDXH20E0tyI9PLS5ITE4Fqox39jM0NDEyNTUyMnA0JkYNAAhFM1o</recordid><startdate>20220329</startdate><enddate>20220329</enddate><creator>MA CHENG</creator><creator>WEI KAI</creator><creator>ZHU XINYING</creator><creator>GAO XIANGYU</creator><creator>CHEN MIN</creator><creator>SUN YULING</creator><creator>LI CONGCONG</creator><creator>WANG JIWEI</creator><creator>LI JIAHUI</creator><creator>ZHANG XUNBING</creator><creator>SUN XUEBEI</creator><creator>WANG BIN</creator><scope>EVB</scope></search><sort><creationdate>20220329</creationdate><title>Weld joint quality detection method based on Transform neural network</title><author>MA CHENG ; WEI KAI ; ZHU XINYING ; GAO XIANGYU ; CHEN MIN ; SUN YULING ; LI CONGCONG ; WANG JIWEI ; LI JIAHUI ; ZHANG XUNBING ; SUN XUEBEI ; WANG BIN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114255220A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>MA CHENG</creatorcontrib><creatorcontrib>WEI KAI</creatorcontrib><creatorcontrib>ZHU XINYING</creatorcontrib><creatorcontrib>GAO XIANGYU</creatorcontrib><creatorcontrib>CHEN MIN</creatorcontrib><creatorcontrib>SUN YULING</creatorcontrib><creatorcontrib>LI CONGCONG</creatorcontrib><creatorcontrib>WANG JIWEI</creatorcontrib><creatorcontrib>LI JIAHUI</creatorcontrib><creatorcontrib>ZHANG XUNBING</creatorcontrib><creatorcontrib>SUN XUEBEI</creatorcontrib><creatorcontrib>WANG BIN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MA CHENG</au><au>WEI KAI</au><au>ZHU XINYING</au><au>GAO XIANGYU</au><au>CHEN MIN</au><au>SUN YULING</au><au>LI CONGCONG</au><au>WANG JIWEI</au><au>LI JIAHUI</au><au>ZHANG XUNBING</au><au>SUN XUEBEI</au><au>WANG BIN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Weld joint quality detection method based on Transform neural network</title><date>2022-03-29</date><risdate>2022</risdate><abstract>The invention discloses a weld joint quality detection method based on a Transform neural network, which comprises the following steps of: S1, additionally arranging a high-speed capacity molten pool monitoring camera at the end, close to a welding gun, of a welding manipulator, acquiring welding shooting image data in real time, and monitoring the states of an electric arc, a molten pool, a groove and the like; s2, basic data enhancement is carried out on the acquired data, a multi-image overlapping enhancement method is used, and the detection efficiency of small targets such as welding seams is improved; s3, a visual Transform neural network welding seam recognition model based on self-attention is constructed; s4, visualizing the change of the training process of the model by adopting a multi-modal related attention method, and adjusting the structure of the model; and S5, detecting the quality of the welding seam by using the trained model. According to the method, the data has relatively high robustness</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114255220A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Weld joint quality detection method based on Transform neural network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T04%3A01%3A34IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=MA%20CHENG&rft.date=2022-03-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114255220A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |