{"id":"https://openalex.org/W7128645686","doi":"https://doi.org/10.1109/tii.2026.3659675","title":"A Novel Fusion Attention-Based Lightweight Model for Pipeline Weld Multiscale Defect Detection","display_name":"A Novel Fusion Attention-Based Lightweight Model for Pipeline Weld Multiscale Defect Detection","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128645686","doi":"https://doi.org/10.1109/tii.2026.3659675"},"language":null,"primary_location":{"id":"doi:10.1109/tii.2026.3659675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2026.3659675","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125653241","display_name":"Songyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I921716337","display_name":"Northeast Petroleum University","ror":"https://ror.org/03net5943","country_code":"CN","type":"education","lineage":["https://openalex.org/I921716337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songyuan Zhang","raw_affiliation_strings":["National Key Laboratory of Continental Shale Oil, Northeast Petroleum University, Daqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Continental Shale Oil, Northeast Petroleum University, Daqing, China","institution_ids":["https://openalex.org/I921716337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046553747","display_name":"Chuang Wang","orcid":"https://orcid.org/0000-0001-8938-9312"},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I921716337","display_name":"Northeast Petroleum University","ror":"https://ror.org/03net5943","country_code":"CN","type":"education","lineage":["https://openalex.org/I921716337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Wang","raw_affiliation_strings":["Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China"],"raw_orcid":"https://orcid.org/0000-0001-8938-9312","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China","institution_ids":["https://openalex.org/I4210094970","https://openalex.org/I921716337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125633851","display_name":"Hongli Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I921716337","display_name":"Northeast Petroleum University","ror":"https://ror.org/03net5943","country_code":"CN","type":"education","lineage":["https://openalex.org/I921716337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Dong","raw_affiliation_strings":["Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China"],"raw_orcid":"https://orcid.org/0000-0001-8531-6757","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China","institution_ids":["https://openalex.org/I4210094970","https://openalex.org/I921716337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101690694","display_name":"Xuefeng Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105529","display_name":"Daqing Oilfield General Hospital","ror":"https://ror.org/01ey7we33","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210105529"]},{"id":"https://openalex.org/I4387155657","display_name":"Daqing Oilfield of CNPC","ror":"https://ror.org/03shhrx95","country_code":null,"type":"company","lineage":["https://openalex.org/I4387155657","https://openalex.org/I98227222"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Zhao","raw_affiliation_strings":["Daqing Oilfield Company Limited, Daqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Daqing Oilfield Company Limited, Daqing, China","institution_ids":["https://openalex.org/I4210105529","https://openalex.org/I4387155657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048082514","display_name":"Chuang Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I921716337","display_name":"Northeast Petroleum University","ror":"https://ror.org/03net5943","country_code":"CN","type":"education","lineage":["https://openalex.org/I921716337"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuang Guan","raw_affiliation_strings":["Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Energy Research Institute, Northeast Petroleum University, Daqing, China","institution_ids":["https://openalex.org/I4210094970","https://openalex.org/I921716337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6069,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88634771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"6","first_page":"5600","last_page":"5611"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10834","display_name":"Welding Techniques and Residual Stresses","score":0.6931999921798706,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10834","display_name":"Welding Techniques and Residual Stresses","score":0.6931999921798706,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.05660000070929527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12086","display_name":"Structural Integrity and Reliability Analysis","score":0.04830000177025795,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/welding","display_name":"Welding","score":0.6158999800682068},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5371000170707703},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4771000146865845},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4429999887943268},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.3928000032901764},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.3707999885082245},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045000195503235},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C19474535","wikidata":"https://www.wikidata.org/wiki/Q131172","display_name":"Welding","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4771000146865845},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42890000343322754},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2026.3659675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2026.3659675","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3066835647","display_name":null,"funder_award_id":"U21A2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3161209015","display_name":null,"funder_award_id":"2024MD753911","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8874280279","display_name":null,"funder_award_id":"62403119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Weld":[0],"defect":[1,40,67,144],"detection":[2,35,68,76,135],"is":[3],"critical":[4],"for":[5,65],"maintaining":[6],"the":[7,31,50,100,124,138,149,169],"safe":[8],"operation":[9],"of":[10,33,91,155],"natural":[11,70],"gas":[12,71],"pipelines.":[13],"While":[14],"computer":[15],"vision-based":[16],"approaches":[17],"have":[18],"emerged":[19],"as":[20],"a":[21,56,83],"promising":[22],"research":[23],"focus,":[24],"existing":[25],"deep":[26],"learning":[27],"models":[28],"inevitably":[29],"face":[30],"problem":[32],"limited":[34],"accuracy":[36,77,174],"in":[37,43,69],"multiscale":[38,105],"welding":[39,46],"detection,":[41],"especially":[42],"recognizing":[44],"tiny":[45,143],"defects.":[47],"To":[48],"overcome":[49],"above":[51],"challenges,":[52],"this":[53],"article":[54],"proposes":[55],"novel":[57],"DySample-guided":[58],"lightweight":[59],"feature":[60,115],"aggregation":[61],"fusion":[62],"network":[63],"(DyLFA-Net)":[64],"weld":[66],"pipelines,":[72],"aiming":[73],"to":[74,141],"improve":[75,142],"and":[78,120,166,175],"computational":[79],"efficiency":[80],"while":[81],"preserving":[82],"compact":[84],"architectural":[85],"design.":[86],"The":[87,96,111],"DyLFA-Net":[88],"model":[89,151,171],"consists":[90],"two":[92],"key":[93],"components.":[94],"1)":[95],"IB-SCSA":[97],"module":[98,113],"at":[99,137],"P5":[101],"layer,":[102],"which":[103],"enhances":[104,114],"semantic":[106],"extraction":[107],"via":[108],"spatial-channel":[109],"attention.":[110],"IB":[112],"expressiveness":[116],"through":[117],"channel":[118],"expansion":[119],"depthwise":[121],"convolution,":[122],"supplying":[123],"SCSA":[125],"mechanism":[126],"with":[127,161],"semantically":[128],"enriched":[129],"input":[130],"features.":[131],"2)":[132],"A":[133],"high-resolution":[134],"head":[136],"P2":[139],"layer":[140],"recognition.":[145],"Experiments":[146],"show":[147],"that":[148],"proposed":[150,170],"achieves":[152],"an":[153],"mAP@0.5":[154],"89.9%,":[156],"outperforming":[157],"mainstream":[158],"detectors.":[159],"Additionally,":[160],"just":[162],"1.31":[163],"M":[164],"parameters":[165],"6.6":[167],"GFLOPs,":[168],"offers":[172],"high":[173],"low":[176],"complexity,":[177],"enabling":[178],"real-time":[179],"deployment":[180],"on":[181],"resource-limited":[182],"edge":[183],"devices.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-12T00:00:00"}