{"id":"https://openalex.org/W4390939996","doi":"https://doi.org/10.1109/tnnls.2023.3340741","title":"Reinforcement Learning for Blast Furnace Ironmaking Operation With Safety and Partial Observation Considerations","display_name":"Reinforcement Learning for Blast Furnace Ironmaking Operation With Safety and Partial Observation Considerations","publication_year":2024,"publication_date":"2024-01-17","ids":{"openalex":"https://openalex.org/W4390939996","doi":"https://doi.org/10.1109/tnnls.2023.3340741","pmid":"https://pubmed.ncbi.nlm.nih.gov/38231813"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3340741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3340741","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5090893698","display_name":"Ke Jiang","orcid":"https://orcid.org/0000-0002-2642-7948"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Ke Jiang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China","Department of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013235835","display_name":"Zhaohui Jiang","orcid":"https://orcid.org/0000-0002-4861-5819"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Jiang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035923986","display_name":"Yongfang Xie","orcid":"https://orcid.org/0000-0002-2060-6574"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongfang Xie","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100711520","display_name":"Weihua Gui","orcid":"https://orcid.org/0000-0002-5337-6445"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Gui","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090893698"],"corresponding_institution_ids":["https://openalex.org/I139660479","https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":4.5498,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94917187,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"35","issue":"3","first_page":"3077","last_page":"3090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.972100019454956,"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":0.972100019454956,"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/T11837","display_name":"Iron and Steelmaking Processes","score":0.9115999937057495,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.909500002861023,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8065648674964905},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7165524959564209},{"id":"https://openalex.org/keywords/profitability-index","display_name":"Profitability index","score":0.6770545840263367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6520235538482666},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5306141972541809},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5052719712257385},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4885588586330414},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4373289942741394},{"id":"https://openalex.org/keywords/process-safety","display_name":"Process safety","score":0.422085165977478},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3717460632324219},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.36469560861587524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.336032897233963},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3190660774707794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2938414216041565},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2815330922603607},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22484198212623596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22110554575920105},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.16964030265808105},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.16440075635910034},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.13469389081001282},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.12741976976394653}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8065648674964905},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7165524959564209},{"id":"https://openalex.org/C129361004","wikidata":"https://www.wikidata.org/wiki/Q2470236","display_name":"Profitability index","level":2,"score":0.6770545840263367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520235538482666},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5306141972541809},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5052719712257385},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4885588586330414},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4373289942741394},{"id":"https://openalex.org/C80038721","wikidata":"https://www.wikidata.org/wiki/Q4380673","display_name":"Process safety","level":3,"score":0.422085165977478},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3717460632324219},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.36469560861587524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336032897233963},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3190660774707794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2938414216041565},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2815330922603607},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22484198212623596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22110554575920105},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.16964030265808105},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.16440075635910034},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.13469389081001282},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.12741976976394653},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2023.3340741","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3340741","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38231813","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38231813","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:dr.ntu.edu.sg:10356/177989","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/177989","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G5456142379","display_name":null,"funder_award_id":"202106370153","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G7186841717","display_name":null,"funder_award_id":"2021RC4054","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2020283003","https://openalex.org/W2050860697","https://openalex.org/W2107726111","https://openalex.org/W2291973609","https://openalex.org/W2560260256","https://openalex.org/W2757342969","https://openalex.org/W2767358759","https://openalex.org/W2772589676","https://openalex.org/W2790924949","https://openalex.org/W2885282028","https://openalex.org/W2908261578","https://openalex.org/W2919115771","https://openalex.org/W2922351830","https://openalex.org/W2927025417","https://openalex.org/W2981970936","https://openalex.org/W3005770546","https://openalex.org/W3012066402","https://openalex.org/W3018109943","https://openalex.org/W3019142787","https://openalex.org/W3023586494","https://openalex.org/W3040686994","https://openalex.org/W3108612728","https://openalex.org/W3110954692","https://openalex.org/W3131678030","https://openalex.org/W3134254543","https://openalex.org/W3172814384","https://openalex.org/W3185895077","https://openalex.org/W3196351275","https://openalex.org/W3198999478","https://openalex.org/W3199799665","https://openalex.org/W3203925970","https://openalex.org/W3207875416","https://openalex.org/W3211700439","https://openalex.org/W4283780580","https://openalex.org/W4285107192","https://openalex.org/W4289515710","https://openalex.org/W4360584316","https://openalex.org/W6684205842","https://openalex.org/W6696783566"],"related_works":["https://openalex.org/W3123911006","https://openalex.org/W4400868993","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W1985560493","https://openalex.org/W2386410636"],"abstract_inverted_index":{"Making":[0],"proper":[1],"decision":[2,35,105,126,157],"online":[3,68],"in":[4,17,23,50,112,177],"complex":[5],"environment":[6],"during":[7],"the":[8,24,56,103,119,140,148,153,166,171,174],"blast":[9],"furnace":[10],"(BF)":[11],"operation":[12,108],"is":[13,115],"a":[14,39,76,136],"key":[15],"factor":[16],"achieving":[18],"long-term":[19],"success":[20],"and":[21,33,70,87,121,130,142,181],"profitability":[22],"steel":[25],"manufacturing":[26],"industry.":[27],"Regulatory":[28],"lags,":[29],"ore":[30],"source":[31],"uncertainty,":[32],"continuous":[34],"requirement":[36],"make":[37,60,125],"it":[38,61,95],"challenging":[40],"task.":[41],"Recently,":[42],"reinforcement":[43],"learning":[44],"(RL)":[45],"has":[46],"demonstrated":[47],"state-of-the-art":[48],"performance":[49],"various":[51],"sequential":[52],"decision-making":[53],"problems.":[54],"However,":[55],"strict":[57],"safety":[58,180],"requirements":[59],"impossible":[62],"to":[63,82,101,124,145],"explore":[64],"optimal":[65,104],"decisions":[66],"through":[67],"trial":[69],"error.":[71],"Therefore,":[72],"this":[73,113],"article":[74],"proposes":[75],"novel":[77],"offline":[78],"RL":[79],"approach":[80],"designed":[81],"ensure":[83],"safety,":[84],"maximize":[85],"return,":[86],"address":[88],"issues":[89],"of":[90,139,173],"partially":[91,154],"observed":[92,155],"states.":[93],"Specifically,":[94],"utilizes":[96],"an":[97],"off-policy":[98],"actor-critic":[99],"framework":[100,114],"infer":[102],"from":[106,161],"expert":[107],"trajectories.":[109],"The":[110],"\"actor\"":[111],"jointly":[116],"trained":[117],"by":[118],"supervision":[120],"evaluation":[122],"signals":[123],"with":[127],"low":[128],"risk":[129],"high":[131],"return.":[132,182],"Furthermore,":[133],"we":[134],"investigate":[135],"recurrent":[137],"version":[138],"actor":[141],"critic":[143],"networks":[144],"better":[146],"capture":[147],"complete":[149],"observations,":[150],"which":[151],"solves":[152],"Markov":[156],"process":[158,169],"(POMDP)":[159],"arising":[160],"sensor":[162],"limitations.":[163],"Verification":[164],"within":[165],"BF":[167],"smelting":[168],"demonstrates":[170],"improvements":[172],"proposed":[175],"algorithm":[176],"performance,":[178],"i.e.,":[179]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
