{"id":"https://openalex.org/W7214927472","doi":"https://doi.org/10.21872/annual2025_8495","title":"Large Language Models for Condition Monitoring: A Feature Encoder-Decoder Framework","display_name":"Large Language Models for Condition Monitoring: A Feature Encoder-Decoder Framework","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7214927472","doi":"https://doi.org/10.21872/annual2025_8495"},"language":"en","primary_location":{"id":"doi:10.21872/annual2025_8495","doi":"https://doi.org/10.21872/annual2025_8495","is_oa":false,"landing_page_url":"https://doi.org/10.21872/annual2025_8495","pdf_url":null,"source":{"id":"https://openalex.org/S7407087832","display_name":"IISE Annual Conference & Expo","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IISE Annual Conference & Expo 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5153570896","display_name":"Haozhou Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhou Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153672082","display_name":"Wei Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153636973","display_name":"Srinivasan Radhakrishnan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasan Radhakrishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135177087","display_name":"Sagar Kamarthi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sagar Kamarthi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76109838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10220","display_name":"Machine Fault Diagnosis Techniques","score":0.9491999745368958,"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/T10220","display_name":"Machine Fault Diagnosis Techniques","score":0.9491999745368958,"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/T10780","display_name":"Reliability and Maintenance Optimization","score":0.023399999365210533,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.00570000009611249,"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/large-language-models","display_name":"large language models","score":0.9589999914169312},{"id":"https://openalex.org/keywords/condition-monitoring","display_name":"condition monitoring","score":0.9909999966621399},{"id":"https://openalex.org/keywords/time-series-features","display_name":"time series features","score":0.6959999799728394},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8320000171661377},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.4830000102519989},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.7379999756813049},{"id":"https://openalex.org/keywords/gpt-2","display_name":"GPT-2","score":0.7590000033378601},{"id":"https://openalex.org/keywords/gemma","display_name":"Gemma","score":0.9240000247955322},{"id":"https://openalex.org/keywords/llama","display_name":"llamas","score":0.9959999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6322000026702881},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4083000123500824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39820000529289246},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21872/annual2025_8495","doi":"https://doi.org/10.21872/annual2025_8495","is_oa":false,"landing_page_url":"https://doi.org/10.21872/annual2025_8495","pdf_url":null,"source":{"id":"https://openalex.org/S7407087832","display_name":"IISE Annual Conference & Expo","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IISE Annual Conference & Expo 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4943999946117401,"id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7136261071","https://openalex.org/W4417308000","https://openalex.org/W4411475608","https://openalex.org/W7152121361","https://openalex.org/W7220439991","https://openalex.org/W4410519729","https://openalex.org/W7221120337","https://openalex.org/W7124833014","https://openalex.org/W7130390393","https://openalex.org/W7025052713"],"abstract_inverted_index":{"The":[0,67,112],"development":[1],"of":[2,69,108,137,176,184,205],"generative":[3],"artificial":[4],"intelligence,":[5],"particularly":[6],"large":[7],"language":[8],"models":[9],"(LLMs),":[10],"offers":[11],"new":[12],"opportunities":[13],"for":[14,41,187],"condition":[15,98,136,208],"monitoring":[16,209],"(CM)":[17],"systems.":[18,80],"Unlike":[19],"conventional":[20],"machine":[21],"learning":[22],"techniques,":[23],"LLMs":[24,73,92,154],"can":[25,127],"identify":[26],"patterns,":[27],"reason":[28],"about":[29],"real-world":[30],"events,":[31],"and":[32,60,71,131,182,203,214],"analyze":[33],"time":[34,123],"series":[35,124],"data":[36,50,63,119],"while":[37],"generating":[38],"human-readable":[39],"explanations":[40],"changes":[42,133],"in":[43,78,114,134],"industrial":[44,65,138],"asset":[45],"conditions.":[46],"However,":[47],"LLMs\u2019":[48],"linguistic":[49],"process":[51],"nature":[52],"makes":[53],"them":[54],"struggle":[55],"with":[56,91,211],"handling":[57],"the":[58,106,109,115,135,151,159,163,174,201,206],"noisy":[59],"high-dimensional":[61],"sensory":[62,118],"from":[64],"assets.":[66,139],"cost":[68],"training":[70],"running":[72],"also":[74],"impeded":[75],"their":[76],"application":[77],"CM":[79,84],"We":[81],"explore":[82],"a":[83,168],"framework":[85,116],"that":[86,126],"combines":[87],"customized":[88],"feature":[89],"encoders":[90],"as":[93],"decoders,":[94],"to":[95,157,179],"achieve":[96],"good":[97],"prediction,":[99],"possibly":[100],"performing":[101],"on-par":[102],"or":[103],"better":[104],"than":[105],"performance":[107],"existing":[110],"approaches.":[111],"encoder":[113,164],"converts":[117],"into":[120,145],"three":[121],"canonical":[122],"features":[125,141],"capture":[128],"both":[129],"abrupt":[130],"gradual":[132],"These":[140],"are":[142,155],"then":[143],"transformed":[144],"open-ended":[146],"question-answer":[147],"style":[148],"prompts.":[149],"In":[150],"decoder":[152],"phase,":[153],"prompted":[156],"learn":[158],"patterns":[160],"generated":[161],"by":[162],"through":[165],"fine-tuning,":[166],"using":[167],"low-rank":[169],"adaptation":[170],"technique,":[171],"which":[172],"reduces":[173],"number":[175],"trainable":[177],"parameters":[178],"between":[180],"0.1%":[181],"1%":[183],"those":[185],"required":[186],"full":[188],"tuning.":[189],"Using":[190],"our":[191],"experiments":[192],"on":[193],"Backblaze":[194],"hard":[195],"disk":[196],"drive":[197],"data,":[198],"we":[199],"demonstrate":[200],"feasibility":[202],"practicality":[204],"LLM-based":[207],"approach":[210],"GPT-2,":[212],"Gemma,":[213],"Llama":[215],"LLMs.":[216]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-01T00:00:00"}