{"id":"https://openalex.org/W7169215918","doi":"https://doi.org/10.1109/access.2026.3714222","title":"Physics-Embedded Hybrid Neural ODE With Digital Twin Residuals for Fault Diagnosis in Grid-Connected Photovoltaic Systems","display_name":"Physics-Embedded Hybrid Neural ODE With Digital Twin Residuals for Fault Diagnosis in Grid-Connected Photovoltaic Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7169215918","doi":"https://doi.org/10.1109/access.2026.3714222"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3714222","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714222","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3714222","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043479229","display_name":"Majdi Mansouri","orcid":"https://orcid.org/0000-0001-6390-4304"},"institutions":[{"id":"https://openalex.org/I47818738","display_name":"Sultan Qaboos University","ror":"https://ror.org/04wq8zb47","country_code":"OM","type":"education","lineage":["https://openalex.org/I47818738"]}],"countries":["OM"],"is_corresponding":true,"raw_author_name":"Majdi Mansouri","raw_affiliation_strings":["Sultan Qaboos University"],"raw_orcid":"https://orcid.org/0000-0001-6390-4304","affiliations":[{"raw_affiliation_string":"Sultan Qaboos University","institution_ids":["https://openalex.org/I47818738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043479229"],"corresponding_institution_ids":["https://openalex.org/I47818738"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72374163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"108891","last_page":"108906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10468","display_name":"Photovoltaic System Optimization Techniques","score":0.2987000048160553,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10468","display_name":"Photovoltaic System Optimization Techniques","score":0.2987000048160553,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.12439999729394913,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10220","display_name":"Machine Fault Diagnosis Techniques","score":0.06360000371932983,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/photovoltaic-system","display_name":"Photovoltaic system","score":0.6895999908447266},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.607699990272522},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.46950000524520874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4578000009059906},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.436599999666214}],"concepts":[{"id":"https://openalex.org/C41291067","wikidata":"https://www.wikidata.org/wiki/Q1897785","display_name":"Photovoltaic system","level":2,"score":0.6895999908447266},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729999780654907},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.607699990272522},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.46950000524520874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C21267803","wikidata":"https://www.wikidata.org/wiki/Q5438159","display_name":"Fault indicator","level":4,"score":0.24959999322891235},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.24950000643730164}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3714222","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714222","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:aae3e66f4bde446585af7f53a6fe3c59","is_oa":false,"landing_page_url":"https://doaj.org/article/aae3e66f4bde446585af7f53a6fe3c59","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,"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":"IEEE Access, Vol 14, Pp 108891-108906 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3714222","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714222","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6156102418899536}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"and":[1,20,52,96,126,164,177,211,214,227,233,251,283,305,331,345,352,360,375,382,391,412,429],"interpretable":[2,413],"fault":[3,25,108,229,277,417,469],"diagnosis":[4,48,109,418],"in":[5,55],"renewable":[6],"energy":[7],"systems":[8],"remains":[9,457],"challenging":[10],"due":[11],"to":[12,101,195,255,309,367],"measurement":[13,314],"noise,":[14],"nonlinear":[15],"operating":[16,127,152,296],"conditions,":[17,451],"model":[18,148],"uncertainty,":[19],"the":[21,68,76,169,217,245,268,320,369,377,401],"presence":[22],"of":[23,49,63,70,78,104,133,225,248,267,322,371],"interacting":[24],"mechanisms.":[26],"This":[27],"paper":[28],"proposes":[29],"a":[30,79,145,410,434],"Physics-Embedded":[31],"Hybrid":[32],"Neural":[33,97,188,218],"Ordinary":[34],"Differential":[35],"Equation":[36],"(PE-HANODE)":[37],"framework":[38,82,113,373,408,440],"augmented":[39],"with":[40,209,341],"Digital":[41,89,425],"Twin":[42,90,426],"(DT)":[43],"residual":[44,91,155,183,252,326,427],"information":[45],"for":[46,173,279,415,444],"robust":[47],"multi-fault,":[50],"non-Gaussian,":[51],"time-varying":[53],"conditions":[54],"grid-connected":[56],"photovoltaic":[57,471],"(PV)":[58],"systems.":[59],"The":[60,111,204,237,265,405,438],"main":[61],"contribution":[62,370],"this":[64],"work":[65],"is":[66,171,271],"not":[67],"introduction":[69],"individual":[71],"new":[72],"learning":[73,220,335,344,432],"components,":[74],"but":[75],"development":[77],"unified":[80],"diagnostic":[81,249,338,380,403,436],"that":[83,157,319],"integrates":[84,114],"complementary":[85,116],"physics-guided":[86,323],"representations,":[87],"lightweight":[88,146,424],"reasoning,":[92],"attention-guided":[93,187],"feature":[94,142,329,397,422],"weighting,":[95,330],"ODE-based":[98],"temporal":[99,197],"modeling":[100],"address":[102],"limitations":[103],"conventional":[105,342],"data-driven":[106,141],"PV":[107,123,276,291,446],"approaches.":[110],"proposed":[112,269,406,439],"three":[115],"components.":[117],"First,":[118],"physics-informed":[119,212,421],"features":[120],"derived":[121],"from":[122,150,287],"electrical":[124],"characteristics":[125],"principles":[128],"provide":[129,394],"physically":[130],"meaningful":[131],"representations":[132],"system":[134,166],"behavior":[135],"rather":[136,180,258],"than":[137,181,259],"relying":[138],"solely":[139],"on":[140,388],"extraction.":[143],"Second,":[144],"DT":[147,205,325],"identified":[149],"healthy":[151],"data":[153,285],"generates":[154],"signals":[156,253],"quantify":[158,368],"deviations":[159],"between":[160,379],"expected":[161],"nominal":[162],"responses":[163],"measured":[165,210],"behavior,":[167],"while":[168,199,452],"SDM":[170],"employed":[172],"physical":[174,262],"consistency":[175],"verification":[176],"parameter":[178],"calibration":[179],"direct":[182,261],"generation.":[184],"Third,":[185],"an":[186,288],"ODE":[189,219],"architecture":[190],"exploits":[191],"continuous":[192],"latent-state":[193],"evolution":[194],"capture":[196],"dependencies":[198],"prioritizing":[200],"diagnostically":[201],"relevant":[202],"features.":[203],"residuals":[206],"are":[207,301,364],"fused":[208],"variables":[213,250],"incorporated":[215],"into":[216,396],"process,":[221],"enabling":[222],"improved":[223],"discrimination":[224],"subtle":[226],"overlapping":[228],"signatures":[230],"under":[231,303,448],"noisy":[232],"incomplete":[234],"sensing":[235],"conditions.":[236,297],"attention":[238,473],"mechanism":[239],"provides":[240,336],"feature-level":[241],"interpretability":[242],"by":[243,419],"highlighting":[244],"relative":[246],"importance":[247,398],"contributing":[254],"classification":[256],"decisions,":[257],"performing":[260],"root-cause":[263],"identification.":[264],"effectiveness":[266],"approach":[270],"validated":[272],"using":[273],"both":[274],"synthetic":[275],"datasets":[278],"controlled":[280],"proof-of-concept":[281],"evaluation":[282],"experimental":[284],"obtained":[286],"emulated":[289],"laboratory-scale":[290],"platform":[292],"representing":[293],"more":[294],"realistic":[295],"Additional":[298],"robustness":[299],"studies":[300],"conducted":[302,366],"Laplace":[304],"uniform":[306],"noise":[307],"perturbations":[308],"evaluate":[310],"resilience":[311],"against":[312],"non-Gaussian":[313],"uncertainty.":[315],"Comparative":[316],"results":[317],"demonstrate":[318],"integration":[321],"features,":[324],"information,":[327],"attention-based":[328],"continuous-time":[332,430,478],"latent":[333],"representation":[334],"consistent":[337],"improvements":[339],"compared":[340],"machine":[343],"recurrent":[346],"neural":[347,465],"network":[348],"baselines,":[349],"including":[350],"LSTM":[351],"GRU":[353],"models.":[354],"Ablation":[355],"studies,":[356],"statistical":[357],"performance":[358,381],"analysis,":[359],"computational":[361,383],"complexity":[362],"evaluations":[363],"further":[365,453],"each":[372],"component":[374],"assess":[376],"trade-off":[378],"requirements.":[384],"Interpretability":[385],"analyses":[386],"based":[387],"attention-weight":[389],"distributions":[390],"fault-confusion":[392],"assessment":[393],"insights":[395],"patterns":[399],"within":[400,433],"learned":[402],"representation.":[404],"PE-HANODE":[407],"offers":[409],"physics-consistent":[411],"solution":[414],"intelligent":[416],"unifying":[420],"construction,":[423],"generation,":[428],"deep":[431],"single":[435],"architecture.":[437],"demonstrates":[441],"promising":[442],"capability":[443],"real-time":[445],"monitoring":[447],"evaluated":[449],"laboratory":[450],"utility-scale":[454],"field":[455],"validation":[456],"necessary":[458],"before":[459],"large-scale":[460],"industrial":[461],"deployment. INDEX":[462],"TERMS":[463]," Physics-embedded":[464],"ODE,":[466],"digital":[467],"twin,":[468],"diagnosis,":[470],"systems,":[472],"mechanism,":[474],"explainable":[475],"artificial":[476],"intelligence,":[477],"learning.":[479]},"counts_by_year":[],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2026-07-17T00:00:00"}