{"id":"https://openalex.org/W7124856973","doi":"https://doi.org/10.3390/a19010084","title":"An Iterative Reinforcement Learning Algorithm for Speed Drop Compensation in Rolling Mills","display_name":"An Iterative Reinforcement Learning Algorithm for Speed Drop Compensation in Rolling Mills","publication_year":2026,"publication_date":"2026-01-18","ids":{"openalex":"https://openalex.org/W7124856973","doi":"https://doi.org/10.3390/a19010084"},"language":"en","primary_location":{"id":"doi:10.3390/a19010084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19010084","pdf_url":"https://www.mdpi.com/1999-4893/19/1/84/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/19/1/84/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021534663","display_name":"Shengyue Zong","orcid":"https://orcid.org/0000-0001-8414-7402"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyue Zong","raw_affiliation_strings":["National Engineering Research Center for Advanced Rolling Technology and Intelligent Manufacturing, University of Science and Technology Beijing, Beijing 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Advanced Rolling Technology and Intelligent Manufacturing, University of Science and Technology Beijing, Beijing 100083, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123437658","display_name":"Jiwei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwei Chen","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014948984","display_name":"Yanpeng Hu","orcid":"https://orcid.org/0000-0003-1346-6953"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanpeng Hu","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018970563","display_name":"Jian Li","orcid":"https://orcid.org/0009-0003-7566-9120"},"institutions":[{"id":"https://openalex.org/I4210118099","display_name":"China Design Group (China)","ror":"https://ror.org/02mnaa826","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210118099"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinyan Li","raw_affiliation_strings":["Nanjing Steel Group Co., Ltd., Nanjing 210035, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing Steel Group Co., Ltd., Nanjing 210035, China","institution_ids":["https://openalex.org/I4210118099"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06088038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"19","issue":"1","first_page":"84","last_page":"84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11201","display_name":"Metallurgy and Material Forming","score":0.9078999757766724,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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/T11201","display_name":"Metallurgy and Material Forming","score":0.9078999757766724,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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/T10188","display_name":"Advanced machining processes and optimization","score":0.017000000923871994,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.014299999922513962,"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/control-theory","display_name":"Control theory (sociology)","score":0.6830999851226807},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5953999757766724},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.5131999850273132},{"id":"https://openalex.org/keywords/slab","display_name":"Slab","score":0.45669999718666077},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42800000309944153},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41119998693466187},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.3758000135421753}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6830999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452000141143799},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.5131999850273132},{"id":"https://openalex.org/C113740112","wikidata":"https://www.wikidata.org/wiki/Q5904738","display_name":"Slab","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C2985318046","wikidata":"https://www.wikidata.org/wiki/Q452648","display_name":"Rolling mill","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C2781345722","wikidata":"https://www.wikidata.org/wiki/Q5308388","display_name":"Drop (telecommunication)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C16057445","wikidata":"https://www.wikidata.org/wiki/Q44494","display_name":"Mill","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.2720000147819519},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C33493971","wikidata":"https://www.wikidata.org/wiki/Q3295893","display_name":"Mass flow","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a19010084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19010084","pdf_url":"https://www.mdpi.com/1999-4893/19/1/84/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2b38b4c00fc94e4e8ce3384cee6fc013","is_oa":true,"landing_page_url":"https://doaj.org/article/2b38b4c00fc94e4e8ce3384cee6fc013","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 19, Iss 1, p 84 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a19010084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a19010084","pdf_url":"https://www.mdpi.com/1999-4893/19/1/84/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124856973.pdf","grobid_xml":"https://content.openalex.org/works/W7124856973.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2003905593","https://openalex.org/W2118220285","https://openalex.org/W2560440155","https://openalex.org/W2775482448","https://openalex.org/W3001491365","https://openalex.org/W3016621379","https://openalex.org/W3017166227","https://openalex.org/W3092258720","https://openalex.org/W3116816022","https://openalex.org/W3169114806","https://openalex.org/W4311168094","https://openalex.org/W4318052364","https://openalex.org/W4323644407","https://openalex.org/W4327662941","https://openalex.org/W4388242073","https://openalex.org/W4392848342","https://openalex.org/W4399202119","https://openalex.org/W4399303890","https://openalex.org/W4403243011","https://openalex.org/W4404817008","https://openalex.org/W4412610146","https://openalex.org/W4413785532","https://openalex.org/W4415741313","https://openalex.org/W7117140393"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,7,12,21,78,125,131,150,156,173,178],"process":[2],"of":[3,11,23,63,98,135,177],"steel":[4],"rolling":[5,13,25,51,82,192],"production,":[6],"speed":[8,194],"reduction":[9],"compensation":[10,34,58,66,72,99,126],"mill":[14,193],"is":[15,60,101,120],"a":[16,32,64,70,90,105,113],"key":[17],"link":[18],"to":[19,44,122],"ensure":[20],"stability":[22],"slab":[24,54,86],"and":[26,80,160,175,190],"product":[27],"quality.":[28],"This":[29],"paper":[30],"proposes":[31],"hybrid":[33,152],"method":[35,180],"that":[36,149],"integrates":[37],"motor":[38,91],"dynamic":[39],"modeling":[40],"with":[41,166,185],"reinforcement":[42,186],"learning":[43,129,187],"minimize":[45],"mass":[46,132,157],"flow":[47,133,158],"error":[48,134,159],"between":[49],"adjacent":[50],"mills":[52],"during":[53],"rolling.":[55],"A":[56],"two-stage":[57],"strategy":[59],"designed,":[61],"consisting":[62],"constant-gain":[65],"phase":[67],"followed":[68],"by":[69,128],"decaying":[71],"phase,":[73],"which":[74],"explicitly":[75],"accounts":[76],"for":[77,110,188],"repetitive":[79],"consistent":[81],"conditions":[83],"in":[84,181],"batch":[85],"production.":[87],"Based":[88],"on":[89],"dynamics-based":[92],"theoretical":[93],"model,":[94],"an":[95],"initial":[96],"estimation":[97],"parameters":[100,127],"first":[102],"obtained,":[103],"providing":[104],"physically":[106],"interpretable":[107],"starting":[108],"point":[109],"optimization.":[111],"Subsequently,":[112],"Deep":[114],"Deterministic":[115],"Policy":[116],"Gradient":[117],"(DDPG)":[118],"algorithm":[119],"employed":[121],"iteratively":[123],"refine":[124],"from":[130],"each":[136],"rolled":[137],"slab,":[138],"enabling":[139],"data-driven":[140],"adaptation":[141],"while":[142],"preserving":[143],"physical":[144],"consistency.":[145],"Simulation":[146],"results":[147,171],"demonstrate":[148],"proposed":[151,179],"approach":[153],"significantly":[154],"reduces":[155],"achieves":[161],"stable":[162],"convergence,":[163],"outperforming":[164],"strategies":[165],"randomly":[167],"initialized":[168],"parameters.":[169],"The":[170],"verify":[172],"effectiveness":[174],"novelty":[176],"combining":[182],"model-based":[183],"insight":[184],"intelligent":[189],"adaptive":[191],"drop":[195],"compensation.":[196]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-21T00:00:00"}