Fan surface defect online detection quantification method based on unmanned aerial vehicle and deep learning
The invention discloses a fan surface defect online detection and quantification method based on an unmanned aerial vehicle and deep learning, and the method comprises the steps: improving a receptive field fixing problem of a network through introducing a moving window self-attention mechanism, des...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
14.06.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses a fan surface defect online detection and quantification method based on an unmanned aerial vehicle and deep learning, and the method comprises the steps: improving a receptive field fixing problem of a network through introducing a moving window self-attention mechanism, designing a lightweight image segmentation module based on a feature pyramid and a feature fusion module, and carrying out the further improvement of a network structure, according to the method, multiple tasks of detecting and segmenting defect features in a fan surface image are realized, and skeleton extraction is carried out on an output semantic feature map by utilizing convex hull fitting and a refining algorithm, so that defect length information and area information are acquired. The actual length of the defect is calculated according to the camera imaging principle, and finally defect damage evaluation is achieved through threshold segmentation. And a data communication link between the unmanned aerial vehicl |
---|---|
AbstractList | The invention discloses a fan surface defect online detection and quantification method based on an unmanned aerial vehicle and deep learning, and the method comprises the steps: improving a receptive field fixing problem of a network through introducing a moving window self-attention mechanism, designing a lightweight image segmentation module based on a feature pyramid and a feature fusion module, and carrying out the further improvement of a network structure, according to the method, multiple tasks of detecting and segmenting defect features in a fan surface image are realized, and skeleton extraction is carried out on an output semantic feature map by utilizing convex hull fitting and a refining algorithm, so that defect length information and area information are acquired. The actual length of the defect is calculated according to the camera imaging principle, and finally defect damage evaluation is achieved through threshold segmentation. And a data communication link between the unmanned aerial vehicl |
Author | FANG JIANHAO TAN JIANRONG ZHAO FENG YAN JIQUAN ZHANG YAXUAN HU WEIFEI JIAO QING ZHANG TONGZHOU |
Author_xml | – fullname: YAN JIQUAN – fullname: ZHAO FENG – fullname: ZHANG TONGZHOU – fullname: ZHANG YAXUAN – fullname: FANG JIANHAO – fullname: TAN JIANRONG – fullname: HU WEIFEI – fullname: JIAO QING |
BookMark | eNqNjj0KAjEUhFNo4d8dngcQDIpoKYuLlZW9PJOJG8i-rJus5zeKB7Ca-eBjmKkaSRRMVKhZKA29YwOycDCZogQvH8qFfBR6DizZO2_4iy1yEy3dOcEWmQZpWaR0Ru850AuNNwHEYssIOgrgXrw85mrsOCQsfjlTy_p0rc4rdPGG1JUPgnyrLlrv9WG33urj5h_nDYLhQ30 |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 基于无人机与深度学习的风机表面缺陷在线检测量化方法 |
ExternalDocumentID | CN118196041A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN118196041A3 |
IEDL.DBID | EVB |
IngestDate | Fri Sep 20 10:14:15 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN118196041A3 |
Notes | Application Number: CN202410331439 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240614&DB=EPODOC&CC=CN&NR=118196041A |
ParticipantIDs | epo_espacenet_CN118196041A |
PublicationCentury | 2000 |
PublicationDate | 20240614 |
PublicationDateYYYYMMDD | 2024-06-14 |
PublicationDate_xml | – month: 06 year: 2024 text: 20240614 day: 14 |
PublicationDecade | 2020 |
PublicationYear | 2024 |
RelatedCompanies | ZHEJIANG UNIVERSITY |
RelatedCompanies_xml | – name: ZHEJIANG UNIVERSITY |
Score | 3.6848156 |
Snippet | The invention discloses a fan surface defect online detection and quantification method based on an unmanned aerial vehicle and deep learning, and the method... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
Title | Fan surface defect online detection quantification method based on unmanned aerial vehicle and deep learning |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240614&DB=EPODOC&locale=&CC=CN&NR=118196041A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3fT8IwEL4g_nxT1Cj-SE3M3hYFy5gPi5GOhZgwiEHDG-nWTjRakG2a-Nd7LUN80cd1y2V36fVbu---AzgXnEpHOI7NhSts6iaJHV02EjtxRYKAEuOuSB_od0On80Dvho1hCV4WtTBGJ_TTiCNiRsWY75lZr6fLQyzfcCvTi-gZhyY3wcDzrWJ3bOCJWn7La_d7fo9ZjHkstMJ7T9dXah2S2u0KrOrPaK2z335s6aqU6W9ICbZhrY_WVLYDpa9xBTbZovNaBTa6xQ_vCqwbhmac4mCRhekuvAZckTSfJfjmREhNyCBzxQu8ygy3SpH3nM95QMYbMu8UTTRoCXyY5OqN6yWWcDMFyYcc6xlEuBJoRE5J0U7iaQ_OgvaAdWx0YPQTrRELl75e7UNZTZQ8AJLo3ItrUVyngvKoeV3nvC4lbUYuAhlvHkL1bzvV_24ewZaOvOZP1egxlLNZLk8QqbPo1IT4G67wmkI |
link.rule.ids | 230,309,786,891,25594,76904 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NT8JAEJ0gfuBNUaP4tSamt0bBpa2HxkhLgwqFGDTcyLa7FY0WpK0m_npnlyJe9NhtM-lsd_Zltm_eAJxyRoXBDUNn3OI6taJID87rkR5ZPEJACTErkgf6Hd9oPdDbQX1QgJd5LYzSCf1U4ogYUSHGe6r268niEMtV3MrkLHjGofGV17ddLc-OFTxRzW3YzV7X7Tqa49iOr_n3tqyvlDok1eslWDYxJZQ6-83HhqxKmfyGFG8DVnpoLU43ofA1KkPJmXdeK8NaJ__hXYZVxdAMExzMozDZglePxSTJphG-OeFCEjLITPECr1LFrYrJe8ZmPCDlDZl1iiYStDg-TLL4jcktljC1BMmHGMkVRFjM0YiYkLydxNM2nHjNvtPS0YHhz2wNHX_h68UOFONxLHaBRDL2wmoQ1iinLDAva4zVhKBmYCGQMXMPKn_bqfx38xhKrX6nPWzf-Hf7sC6_guRSVekBFNNpJg4RtdPgSE33NwyunS0 |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Fan+surface+defect+online+detection+quantification+method+based+on+unmanned+aerial+vehicle+and+deep+learning&rft.inventor=YAN+JIQUAN&rft.inventor=ZHAO+FENG&rft.inventor=ZHANG+TONGZHOU&rft.inventor=ZHANG+YAXUAN&rft.inventor=FANG+JIANHAO&rft.inventor=TAN+JIANRONG&rft.inventor=HU+WEIFEI&rft.inventor=JIAO+QING&rft.date=2024-06-14&rft.externalDBID=A&rft.externalDocID=CN118196041A |