{"id":"https://openalex.org/W4406258208","doi":"https://doi.org/10.1109/tii.2024.3523563","title":"Optimizing Weights to Fit Parametric Operation Policies for Generalized Working Conditions in Linear Systems Using Deep Reinforcement Learning","display_name":"Optimizing Weights to Fit Parametric Operation Policies for Generalized Working Conditions in Linear Systems Using Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4406258208","doi":"https://doi.org/10.1109/tii.2024.3523563"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2024.3523563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3523563","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/A5020341921","display_name":"Ruiyu Qiu","orcid":"https://orcid.org/0009-0004-2458-049X"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyu Qiu","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-2458-049X","affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100553051","display_name":"Guanghui Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Yang","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","Huzhou Institute of Industrial Control Technology, Huzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]},{"raw_affiliation_string":"Huzhou Institute of Industrial Control Technology, Huzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020120796","display_name":"Zuhua Xu","orcid":"https://orcid.org/0000-0002-7873-9521"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuhua Xu","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7873-9521","affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100886581","display_name":"Zhijiang Shao","orcid":"https://orcid.org/0000-0003-3016-4658"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijiang Shao","raw_affiliation_strings":["State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","Huzhou Institute of Industrial Control Technology, Huzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3016-4658","affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]},{"raw_affiliation_string":"Huzhou Institute of Industrial Control Technology, Huzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.00687877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":"4","first_page":"3186","last_page":"3195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901999831199646,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901999831199646,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9646999835968018,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9643999934196472,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/setpoint","display_name":"Setpoint","score":0.865714430809021},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7389026284217834},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6420717835426331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5886397361755371},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5588468909263611},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5588459372520447},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5539518594741821},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.539101243019104},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45056644082069397},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43056559562683105},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.41845738887786865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39836210012435913},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.38384294509887695},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3634452223777771},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3418099284172058},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.284305214881897},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2598195970058441},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1689389944076538},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.08776310086250305}],"concepts":[{"id":"https://openalex.org/C12302492","wikidata":"https://www.wikidata.org/wiki/Q1752097","display_name":"Setpoint","level":2,"score":0.865714430809021},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7389026284217834},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6420717835426331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5886397361755371},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5588468909263611},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5588459372520447},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5539518594741821},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.539101243019104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45056644082069397},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43056559562683105},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.41845738887786865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39836210012435913},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.38384294509887695},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3634452223777771},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3418099284172058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.284305214881897},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2598195970058441},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1689389944076538},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.08776310086250305},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tii.2024.3523563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2024.3523563","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G2914172257","display_name":null,"funder_award_id":"62120106003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G827929139","display_name":null,"funder_award_id":"62173301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8748832732","display_name":null,"funder_award_id":"2021C01151","funder_id":"https://openalex.org/F8142712028","funder_display_name":"Key Research and Development Program of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F8142712028","display_name":"Key Research and Development Program of Zhejiang Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W107451943","https://openalex.org/W1492106702","https://openalex.org/W1969475749","https://openalex.org/W2044979206","https://openalex.org/W2050204013","https://openalex.org/W2140246545","https://openalex.org/W2145339207","https://openalex.org/W2484300557","https://openalex.org/W2811311761","https://openalex.org/W2905429820","https://openalex.org/W2909518001","https://openalex.org/W2919115771","https://openalex.org/W2951360122","https://openalex.org/W2987048079","https://openalex.org/W3023586494","https://openalex.org/W3082598040","https://openalex.org/W3129320545","https://openalex.org/W3168411864","https://openalex.org/W4212838469","https://openalex.org/W4285024875","https://openalex.org/W4317513022","https://openalex.org/W6627932998","https://openalex.org/W6732665253","https://openalex.org/W6747473740","https://openalex.org/W6774966973","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W1495927848","https://openalex.org/W4205962020","https://openalex.org/W2620138946","https://openalex.org/W90946887","https://openalex.org/W191702426","https://openalex.org/W2667392788","https://openalex.org/W172676736","https://openalex.org/W2169601993","https://openalex.org/W1971292522","https://openalex.org/W2807469667"],"abstract_inverted_index":{"At":[0],"present,":[1],"working":[2,132],"conditions":[3],"are":[4,12,53,140,164],"becoming":[5],"more":[6,13,130],"complex,":[7],"and":[8,31,40,49,58,79,116,120,175,182,204,209],"operation":[9,69,138],"policy":[10,151,177],"requirements":[11],"diverse":[14],"in":[15,33,55,61,76,142,178,207,213],"process":[16,22],"system":[17],"engineering.":[18],"To":[19],"control":[20,52],"a":[21,24,114,117,159,179,194,214],"problem,":[23],"balance":[25],"must":[26],"be":[27,38,64,74,127,153],"found":[28],"between":[29,172],"speed":[30],"stability,":[32],"that":[34,200],"operations":[35],"should":[36],"sometimes":[37],"faster":[39],"other":[41],"times":[42],"smoother.":[43],"Traditional":[44],"controllers,":[45],"such":[46],"as":[47,193],"PID":[48],"model":[50],"predictive":[51],"applied":[54,128,183],"various":[56],"problems,":[57],"some":[59],"parameters":[60],"controllers":[62],"can":[63,73,126,152],"used":[65],"to":[66,93,107,129,184],"represent":[67],"the":[68,109,149,169,173],"policy.":[70],"However,":[71],"there":[72],"difficulties":[75],"tuning":[77],"parameters,":[78],"time":[80],"costs":[81],"of":[82,136,161],"online":[83],"calculation.":[84],"This":[85],"article":[86],"proposes":[87],"parametric":[88],"deep":[89],"reinforcement":[90],"learning":[91],"(PDRL)":[92],"replace":[94],"traditional":[95],"controllers.":[96],"PDRL":[97,201],"has":[98,202],"two":[99],"parts.":[100],"A":[101,187],"vanilla":[102],"DRL":[103],"framework":[104],"is":[105,191],"adapted":[106],"solve":[108],"setpoint":[110],"tracking":[111],"problem.":[112],"With":[113,144],"state":[115],"reward":[118],"function":[119],"robust":[121],"training":[122],"tricks,":[123],"trained":[124,141],"agents":[125,135,157],"generalized":[131,185,210],"conditions.":[133,186],"Base":[134],"different":[137],"policies":[139],"advance.":[143],"target":[145,150,174],"performance":[146],"from":[147],"operators,":[148],"fitted":[154,176],"by":[155,167],"base":[156],"with":[158],"set":[160],"weights,":[162],"which":[163],"first":[165],"optimized":[166],"minimizing":[168],"squared":[170],"error":[171],"basic":[180,208],"task,":[181],"shell":[188],"benchmark":[189],"problem":[190],"chosen":[192],"case":[195],"study,":[196],"whose":[197],"results":[198],"show":[199],"feasibility":[203],"stability":[205],"both":[206],"tasks,":[211],"even":[212],"noisy":[215],"environment.":[216]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
