SLM printing defect detection and repair method and system based on deep learning network
The invention discloses an SLM printing defect detection and repair method and system based on a deep learning network, and belongs to the technical field of additive manufacturing, and the method comprises the steps: training a first neural network model through a defect data set, and obtaining a d...
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 | YANG ZIHAN ZHANG GUOQING JIA YONGZHEN LU XIANGYU ZHAO JUNLAI HIGASHIYOSHI |
| description | The invention discloses an SLM printing defect detection and repair method and system based on a deep learning network, and belongs to the technical field of additive manufacturing, and the method comprises the steps: training a first neural network model through a defect data set, and obtaining a defect recognition model; in the printing process of a to-be-detected part, online defect recognition is carried out through the defect recognition model; if the current layer has no defect, continuing to perform powder laying printing of the next layer; if the current layer recognizes the defect, selecting whether to repair the defect or not according to the defect type; if defect repairing is carried out, after printing of the current layer is completed, powder laying is paused for one time, a pre-trained second neural network model is adopted for predicting laser remelting parameters, and laser remelting repairing is carried out till the current layer is free of defects; and the processes of online defect identif |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118218617A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118218617A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118218617A3</originalsourceid><addsrcrecordid>eNrjZIgM9vFVKCjKzCvJzEtXSElNS00uAVIlQCozP08hMS9FoSi1IDGzSCE3tSQjPwUsUlxZXJKaq5CUWJyaogBUlZKaWqCQk5pYlAcyJC-1pDy_KJuHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmpwJVxjv7GRpaGBlamBmaOxoTowYAoAM6Sg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SLM printing defect detection and repair method and system based on deep learning network</title><source>esp@cenet</source><creator>YANG ZIHAN ; ZHANG GUOQING ; JIA YONGZHEN ; LU XIANGYU ; ZHAO JUNLAI ; HIGASHIYOSHI</creator><creatorcontrib>YANG ZIHAN ; ZHANG GUOQING ; JIA YONGZHEN ; LU XIANGYU ; ZHAO JUNLAI ; HIGASHIYOSHI</creatorcontrib><description>The invention discloses an SLM printing defect detection and repair method and system based on a deep learning network, and belongs to the technical field of additive manufacturing, and the method comprises the steps: training a first neural network model through a defect data set, and obtaining a defect recognition model; in the printing process of a to-be-detected part, online defect recognition is carried out through the defect recognition model; if the current layer has no defect, continuing to perform powder laying printing of the next layer; if the current layer recognizes the defect, selecting whether to repair the defect or not according to the defect type; if defect repairing is carried out, after printing of the current layer is completed, powder laying is paused for one time, a pre-trained second neural network model is adopted for predicting laser remelting parameters, and laser remelting repairing is carried out till the current layer is free of defects; and the processes of online defect identif</description><language>chi ; eng</language><subject>ADDITIVE MANUFACTURING TECHNOLOGY ; ADDITIVE MANUFACTURING, i.e. MANUFACTURING OFTHREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVEAGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING,STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING ; CALCULATING ; CASTING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; MAKING METALLIC POWDER ; MANUFACTURE OF ARTICLES FROM METALLIC POWDER ; PERFORMING OPERATIONS ; PHYSICS ; POWDER METALLURGY ; TRANSPORTING ; WORKING METALLIC POWDER</subject><creationdate>2024</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=20240621&DB=EPODOC&CC=CN&NR=118218617A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25566,76549</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240621&DB=EPODOC&CC=CN&NR=118218617A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YANG ZIHAN</creatorcontrib><creatorcontrib>ZHANG GUOQING</creatorcontrib><creatorcontrib>JIA YONGZHEN</creatorcontrib><creatorcontrib>LU XIANGYU</creatorcontrib><creatorcontrib>ZHAO JUNLAI</creatorcontrib><creatorcontrib>HIGASHIYOSHI</creatorcontrib><title>SLM printing defect detection and repair method and system based on deep learning network</title><description>The invention discloses an SLM printing defect detection and repair method and system based on a deep learning network, and belongs to the technical field of additive manufacturing, and the method comprises the steps: training a first neural network model through a defect data set, and obtaining a defect recognition model; in the printing process of a to-be-detected part, online defect recognition is carried out through the defect recognition model; if the current layer has no defect, continuing to perform powder laying printing of the next layer; if the current layer recognizes the defect, selecting whether to repair the defect or not according to the defect type; if defect repairing is carried out, after printing of the current layer is completed, powder laying is paused for one time, a pre-trained second neural network model is adopted for predicting laser remelting parameters, and laser remelting repairing is carried out till the current layer is free of defects; and the processes of online defect identif</description><subject>ADDITIVE MANUFACTURING TECHNOLOGY</subject><subject>ADDITIVE MANUFACTURING, i.e. MANUFACTURING OFTHREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVEAGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING,STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING</subject><subject>CALCULATING</subject><subject>CASTING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>MAKING METALLIC POWDER</subject><subject>MANUFACTURE OF ARTICLES FROM METALLIC POWDER</subject><subject>PERFORMING OPERATIONS</subject><subject>PHYSICS</subject><subject>POWDER METALLURGY</subject><subject>TRANSPORTING</subject><subject>WORKING METALLIC POWDER</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZIgM9vFVKCjKzCvJzEtXSElNS00uAVIlQCozP08hMS9FoSi1IDGzSCE3tSQjPwUsUlxZXJKaq5CUWJyaogBUlZKaWqCQk5pYlAcyJC-1pDy_KJuHgTUtMac4lRdKczMourmGOHvophbkx6cWFyQmpwJVxjv7GRpaGBlamBmaOxoTowYAoAM6Sg</recordid><startdate>20240621</startdate><enddate>20240621</enddate><creator>YANG ZIHAN</creator><creator>ZHANG GUOQING</creator><creator>JIA YONGZHEN</creator><creator>LU XIANGYU</creator><creator>ZHAO JUNLAI</creator><creator>HIGASHIYOSHI</creator><scope>EVB</scope></search><sort><creationdate>20240621</creationdate><title>SLM printing defect detection and repair method and system based on deep learning network</title><author>YANG ZIHAN ; ZHANG GUOQING ; JIA YONGZHEN ; LU XIANGYU ; ZHAO JUNLAI ; HIGASHIYOSHI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118218617A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>ADDITIVE MANUFACTURING TECHNOLOGY</topic><topic>ADDITIVE MANUFACTURING, i.e. MANUFACTURING OFTHREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVEAGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING,STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING</topic><topic>CALCULATING</topic><topic>CASTING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>MAKING METALLIC POWDER</topic><topic>MANUFACTURE OF ARTICLES FROM METALLIC POWDER</topic><topic>PERFORMING OPERATIONS</topic><topic>PHYSICS</topic><topic>POWDER METALLURGY</topic><topic>TRANSPORTING</topic><topic>WORKING METALLIC POWDER</topic><toplevel>online_resources</toplevel><creatorcontrib>YANG ZIHAN</creatorcontrib><creatorcontrib>ZHANG GUOQING</creatorcontrib><creatorcontrib>JIA YONGZHEN</creatorcontrib><creatorcontrib>LU XIANGYU</creatorcontrib><creatorcontrib>ZHAO JUNLAI</creatorcontrib><creatorcontrib>HIGASHIYOSHI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YANG ZIHAN</au><au>ZHANG GUOQING</au><au>JIA YONGZHEN</au><au>LU XIANGYU</au><au>ZHAO JUNLAI</au><au>HIGASHIYOSHI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SLM printing defect detection and repair method and system based on deep learning network</title><date>2024-06-21</date><risdate>2024</risdate><abstract>The invention discloses an SLM printing defect detection and repair method and system based on a deep learning network, and belongs to the technical field of additive manufacturing, and the method comprises the steps: training a first neural network model through a defect data set, and obtaining a defect recognition model; in the printing process of a to-be-detected part, online defect recognition is carried out through the defect recognition model; if the current layer has no defect, continuing to perform powder laying printing of the next layer; if the current layer recognizes the defect, selecting whether to repair the defect or not according to the defect type; if defect repairing is carried out, after printing of the current layer is completed, powder laying is paused for one time, a pre-trained second neural network model is adopted for predicting laser remelting parameters, and laser remelting repairing is carried out till the current layer is free of defects; and the processes of online defect identif</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118218617A |
| source | esp@cenet |
| subjects | ADDITIVE MANUFACTURING TECHNOLOGY ADDITIVE MANUFACTURING, i.e. MANUFACTURING OFTHREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVEAGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING,STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING CALCULATING CASTING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL MAKING METALLIC POWDER MANUFACTURE OF ARTICLES FROM METALLIC POWDER PERFORMING OPERATIONS PHYSICS POWDER METALLURGY TRANSPORTING WORKING METALLIC POWDER |
| title | SLM printing defect detection and repair method and system based on deep learning network |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T18%3A41%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=YANG%20ZIHAN&rft.date=2024-06-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118218617A%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 |