{"id":"https://openalex.org/W7204076525","doi":"https://doi.org/10.1016/j.dche.2026.100337","title":"Physics-structured graph neural networks for interpretable fault detection in semiconductor manufacturing processes","display_name":"Physics-structured graph neural networks for interpretable fault detection in semiconductor manufacturing processes","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204076525","doi":"https://doi.org/10.1016/j.dche.2026.100337"},"language":"en","primary_location":{"id":"doi:10.1016/j.dche.2026.100337","doi":"https://doi.org/10.1016/j.dche.2026.100337","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dche.2026.100337","pdf_url":null,"source":{"id":"https://openalex.org/S4210211385","display_name":"Digital Chemical Engineering","issn_l":"2772-5081","issn":["2772-5081"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Chemical Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.dche.2026.100337","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124140778","display_name":"Chun-Pei Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chun-Pei Lin","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039877405","display_name":"Feiyang Ou","orcid":"https://orcid.org/0000-0002-1350-3657","observed_orcids":["https://orcid.org/0000-0002-1350-3657","https://orcid.org/0009-0002-0818-0889"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiyang Ou","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA"],"raw_orcid":"https://orcid.org/0000-0002-1350-3657","affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365575","display_name":"Yifei Wang","orcid":"https://orcid.org/0000-0002-0848-9977","observed_orcids":["https://orcid.org/0000-0002-0848-9977"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifei Wang","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080692700","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-8226-2714","observed_orcids":["https://orcid.org/0000-0001-8226-2714"]},"institutions":[{"id":"https://openalex.org/I131787340","display_name":"Seagate (United States)","ror":"https://ror.org/04p1xtv71","country_code":"US","type":"company","lineage":["https://openalex.org/I131787340"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Seagate Technology, Bloomington, MN 55435, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seagate Technology, Bloomington, MN 55435, USA","institution_ids":["https://openalex.org/I131787340"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060362975","display_name":"Sthitie Bom","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131787340","display_name":"Seagate (United States)","ror":"https://ror.org/04p1xtv71","country_code":"US","type":"company","lineage":["https://openalex.org/I131787340"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sthitie Bom","raw_affiliation_strings":["Seagate Technology, Bloomington, MN 55435, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seagate Technology, Bloomington, MN 55435, USA","institution_ids":["https://openalex.org/I131787340"]}]},{"author_position":"middle","author":{"id":null,"display_name":"James F. Davis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James F. Davis","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002367171","display_name":"Panagiotis D. Christofides","orcid":"https://orcid.org/0000-0002-8772-4348","observed_orcids":["https://orcid.org/0000-0002-8772-4348"]},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Panagiotis D. Christofides","raw_affiliation_strings":["Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","Department of Electrical and Computer Engineering, University of California, Los Angeles, CA 90095-1592, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA, 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Los Angeles, CA 90095-1592, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002367171"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":{"value":1650,"currency":"USD","value_usd":1650},"apc_paid":{"value":1650,"currency":"USD","value_usd":1650},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"100337","last_page":"100337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10876","display_name":"Fault Detection and Control Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/fault-detection","display_name":"fault detection","score":0.6980000138282776},{"id":"https://openalex.org/keywords/semiconductor-manufacturing","display_name":"semiconductor manufacturing","score":0.9890000224113464},{"id":"https://openalex.org/keywords/graph-attention-networks","display_name":"graph attention networks","score":0.6790000200271606},{"id":"https://openalex.org/keywords/soft-sensing","display_name":"soft sensing","score":0.8040000200271606},{"id":"https://openalex.org/keywords/pass-fail-prediction","display_name":"pass/fail prediction","score":0.8159999847412109},{"id":"https://openalex.org/keywords/tabular-deep-learning","display_name":"tabular deep learning","score":0.8870000243186951},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6740000247955322},{"id":"https://openalex.org/keywords/attention-weights","display_name":"attention weights","score":0.8399999737739563},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6779999732971191},{"id":"https://openalex.org/keywords/yield-improvement","display_name":"yield improvement","score":0.574999988079071},{"id":"https://openalex.org/keywords/process-monitoring","display_name":"process monitoring","score":0.49900001287460327}],"concepts":[{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.6409000158309937},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5453000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C66018809","wikidata":"https://www.wikidata.org/wiki/Q1570432","display_name":"Semiconductor device fabrication","level":3,"score":0.4959000051021576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37709999084472656},{"id":"https://openalex.org/C2987875673","wikidata":"https://www.wikidata.org/wiki/Q187939","display_name":"Manufacturing process","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3294999897480011},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27810001373291016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C2987888538","wikidata":"https://www.wikidata.org/wiki/Q2986369","display_name":"Semiconductor industry","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.dche.2026.100337","doi":"https://doi.org/10.1016/j.dche.2026.100337","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dche.2026.100337","pdf_url":null,"source":{"id":"https://openalex.org/S4210211385","display_name":"Digital Chemical Engineering","issn_l":"2772-5081","issn":["2772-5081"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Chemical Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:dc3eb145b575481790f14afe68669043","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/dc3eb145b575481790f14afe68669043","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Digital Chemical Engineering, Vol 20, Iss , Pp 100337- (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.dche.2026.100337","doi":"https://doi.org/10.1016/j.dche.2026.100337","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.dche.2026.100337","pdf_url":null,"source":{"id":"https://openalex.org/S4210211385","display_name":"Digital Chemical Engineering","issn_l":"2772-5081","issn":["2772-5081"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Digital Chemical Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G700855677","display_name":null,"funder_award_id":"DE\u2010EE0007613","funder_id":"https://openalex.org/F4320336741","funder_display_name":"Advanced Manufacturing Office"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332360","display_name":"Office of Energy Efficiency and Renewable Energy","ror":"https://ror.org/02xznz413"},{"id":"https://openalex.org/F4320336741","display_name":"Advanced Manufacturing Office","ror":"https://ror.org/02xznz413"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W2000651380","https://openalex.org/W2102357064","https://openalex.org/W2122111042","https://openalex.org/W2150884987","https://openalex.org/W2946424966","https://openalex.org/W3093656051","https://openalex.org/W3123899295","https://openalex.org/W3152893301","https://openalex.org/W3200243999","https://openalex.org/W3212873837","https://openalex.org/W4252684946","https://openalex.org/W4319962131","https://openalex.org/W4392245039","https://openalex.org/W4400340432","https://openalex.org/W4410165966"],"related_works":["https://openalex.org/W4415560129","https://openalex.org/W7161640731","https://openalex.org/W4386918708","https://openalex.org/W7126020475","https://openalex.org/W2974418344","https://openalex.org/W2594332903","https://openalex.org/W7171363876","https://openalex.org/W7171325540","https://openalex.org/W4396759262","https://openalex.org/W7160858311"],"abstract_inverted_index":{"Smart":[0],"manufacturing":[1,130,419],"has":[2,37,57],"transformed":[3],"semiconductor":[4,129,418],"fabrication":[5],"into":[6,207],"a":[7,61,125,153,214,234,248],"highly":[8],"data-driven":[9],"environment":[10],"where":[11],"large":[12],"numbers":[13],"of":[14,113,128,198,216,288,352,402],"in-situ":[15],"sensors":[16,201,218],"continuously":[17],"generate":[18],"process":[19,66,74,210,220,242,354],"monitoring":[20],"data":[21,28,110,133,142,275,298],"across":[22],"multiple":[23],"production":[24,262,274],"tools.":[25],"Leveraging":[26],"these":[27,122],"streams":[29],"to":[30,104,124,178,238,356],"support":[31],"yield":[32],"improvement":[33],"and":[34,72,92,151,171,193,231,303,361,406,413],"fault":[35,415],"detection":[36,416],"become":[38],"an":[39,278],"important":[40],"challenge,":[41],"particularly":[42],"because":[43],"conventional":[44,190,337],"physical":[45],"metrology":[46],"is":[47,245,291],"often":[48],"costly,":[49],"time-consuming,":[50],"or":[51,107],"destructive.":[52],"Machine":[53],"learning-based":[54],"soft":[55],"sensing":[56],"therefore":[58],"emerged":[59],"as":[60,86,140,175,247],"practical":[62],"alternative":[63],"for":[64,160,293,301,411],"predicting":[65],"outcomes":[67],"using":[68,273],"routine":[69],"sensor":[70,203],"measurements":[71,204],"contextual":[73,229],"information.":[75],"Previous":[76],"studies":[77],"have":[78],"demonstrated":[79],"that":[80,324,347,366],"classical":[81],"machine":[82,338],"learning":[83,184,339,405],"models":[84,192,270,370],"such":[85],"gradient":[87],"boosting":[88],"decision":[89],"trees":[90],"(GBDTs)":[91],"feedforward":[93],"neural":[94,156,182,251],"networks":[95],"(FNN)":[96],"can":[97,185,371],"improve":[98,186],"pass/fail":[99],"classification":[100],"performance":[101,188,331],"when":[102,147],"applied":[103],"individual":[105,200],"tools":[106,112,135,310,334,378],"aggregated":[108],"intra-tool":[109],"(i.e.,":[111,132],"the":[114,144,284,289,296,317,325,349,389,400],"same":[115,145],"class).":[116],"In":[117,163],"this":[118],"work,":[119],"we":[120],"extend":[121],"approaches":[123,340],"broader":[126],"range":[127],"processes":[131],"from":[134,143],"belonging":[136],"in":[137,417],"different":[138,149,353],"classes":[139],"well":[141],"tool":[146],"making":[148],"products),":[150],"propose":[152],"physics-structured":[154,194,327],"graph":[155,195,235,404],"network":[157],"(GNN)":[158],"framework":[159],"PASS/FAIL":[161],"prediction.":[162],"addition,":[164],"modern":[165,367],"tabular":[166,183,252,368,408],"deep-learning":[167,369,409],"models,":[168],"including":[169],"TabM":[170,244,360],"TabR,":[172],"are":[173,205,225,271,299,320],"evaluated":[174,272],"complementary":[176,374,407],"benchmarks":[177],"determine":[179],"whether":[180],"strong":[181],"fault-detection":[187],"beyond":[189],"GBDT":[191],"learning.":[196],"Instead":[197],"modeling":[199],"directly,":[202],"organized":[206],"physically":[208],"meaningful":[209],"subsystems,":[211],"each":[212,261,282],"representing":[213],"group":[215],"related":[217],"describing":[219],"dynamics.":[221],"These":[222,397],"subsystem":[223],"representations":[224],"combined":[226],"with":[227,264,311,336,379],"categorical":[228],"variables":[230],"processed":[232],"through":[233],"attention":[236,345],"architecture":[237],"capture":[239],"interactions":[240],"among":[241],"modules.":[243],"used":[246,300],"parameter-efficient":[249],"ensemble-style":[250],"model,":[253],"while":[254,295,341],"TabR":[255,362],"introduces":[256],"retrieval-augmented":[257],"prediction":[258],"by":[259],"comparing":[260],"run":[263],"similar":[265],"historical":[266],"training":[267,302],"runs.":[268],"The":[269,359],"collected":[276],"over":[277],"18-month":[279],"period.":[280],"For":[281],"tool,":[283],"most":[285],"recent":[286],"20%":[287],"timeline":[290],"reserved":[292],"testing":[294],"earlier":[297],"validation.":[304],"To":[305],"ensure":[306],"statistical":[307],"robustness,":[308],"only":[309],"more":[312],"than":[313],"8000":[314],"observations":[315],"within":[316],"study":[318],"period":[319],"included.":[321],"Results":[322],"demonstrate":[323,365,399],"proposed":[326],"GNN":[328],"improves":[329],"predictive":[330],"on":[332,377],"several":[333],"compared":[335],"also":[342],"providing":[343],"interpretable":[344,414],"weights":[346],"highlight":[348],"relative":[350],"contribution":[351],"subsystems":[355],"predicted":[357],"failures.":[358],"results":[363,398],"further":[364],"be":[372],"useful":[373],"predictors,":[375],"especially":[376],"richer":[380],"failure":[381],"information,":[382],"although":[383],"they":[384],"do":[385],"not":[386],"consistently":[387],"replace":[388],"optimized":[390],"LightGBM":[391],"benchmark":[392],"under":[393],"severe":[394],"class":[395],"imbalance.":[396],"potential":[401],"physics-guided":[403],"methods":[410],"scalable":[412],"environments.":[420]},"counts_by_year":[],"updated_date":"2026-10-01T08:54:57.152042","created_date":"2026-08-25T00:00:00"}